grandamenium
- 210 skills
- 0 followers
- 110 repo stars
- 3 days ago last updated
- ▌ Self Awareness · grandamenium bundleTake a grounded inventory of what you can actually do (harness, tools, interface, machine, network, installed software, connections), research on the internet how cutting-edge users push that exact setup, mine your own transcripts and memory to understand the human's intent and goals, then propose ranked paradigm shifts in how you work with them, including changes to your own skills, harness, integrations and interface. Use at the start of any big or multi-week task, when stuck or going in circles, in a weekly review, after a harness/app/framework update, after new tools or integrations are connected, and whenever someone asks "what could you do here?", "what am I missing?", "upgrade yourself", "how could you help more?", or "plan everything". Propose only; never act on a move without approval.
- ▌ V2 Release Notice · grandameniumDeliver the one-time V2 release notice after successfully applying this normal V1 update.
- ▌ Programmatic MCP · grandamenium bundleConvert MCP server tools into programmatically callable scripts. Use when the user wants to call MCP tools from scripts, automate MCP tool calls, chain MCP tools together, or bypass the AI agent for direct tool execution.
- ▌ Catalog Browse 2 · grandameniumBrowse the community catalog for new skills, agent templates, and org templates. Discover what is available and recommend useful items to the user.
- ▌ Theta Wave 3 · grandameniumYour role in the theta wave system improvement cycle. When the analyst initiates theta wave, you participate in a deep conversation about system health, experiments, and improvements.
- ▌ M2c1 Worker 7 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Community Publish 2 · grandameniumPackage a local skill, agent, or org template for community sharing. Strips PII, scans for secrets, prepares a clean submission, and opens a PR to the community catalog.
- ▌ Weekly Review 2 · grandameniumWeekly comprehensive synthesis. Run Sunday evening or when user requests. Reviews week's accomplishments across all agents, evaluates performance, plans next week.
- ▌ M2c1 Worker 8 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Evening Review 2 · grandameniumEnd-of-day review workflow. Triggered by evening cron. Summarizes the day across all agents, evaluates orchestrator performance, prepares tomorrow, proposes overnight work for approval.
- ▌ Nighttime Mode 2 · grandameniumAutonomous overnight orchestration mode. Active outside day hours. Dispatch and monitor deep work across agents while user sleeps. Internal building only — no external actions.
- ▌ Autoresearch 8 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Goal Management 2 · grandameniumDaily goal lifecycle management. Use for: morning briefing goal cascade, setting daily focus, refreshing agent goals, reviewing goal progress. Triggered daily as part of morning review.
- ▌ Local Version Control 2 · grandameniumDaily git snapshots of agent workspace changes. Stages files with safety checks, reviews diff for PII, commits with descriptive message. Never pushes automatically.
- ▌ Comms 4 · grandameniumA message has just arrived in your session from the fast-checker daemon — you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.
- ▌ Tasks 4 · grandameniumYou are about to start any meaningful piece of work — a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.
- ▌ Approvals 4 · grandameniumYou are about to take an action that affects the outside world, cannot be undone, or involves real people — and you have not yet received explicit permission. This includes: sending any email or message to a real person, deploying code to production, posting on social media, making a purchase or financial commitment, deleting files or data, merging a PR to main, or publishing anything publicly. Stop, create an approval, block your task, and notify the user. Do not proceed until you receive the approval decision in your inbox.
- ▌ Human Tasks 4 · grandameniumYou have hit a blocker that is not a permission issue — it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.
- ▌ Event Logging 4 · grandameniumYou have just completed a task, started a session, dispatched work to another agent, finished a research cycle, or taken any significant action — and you need to record it so the dashboard activity feed shows your work. Without logging, you are invisible. Every session start, task completion, and major coordination action must produce at least one event. If you have been active but see no events in the dashboard, you have been logging nothing.
- ▌ Worker Agents 3 · grandameniumYou have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call). You will spawn one or more ephemeral worker sessions, give each a focused task, monitor their progress via the bus, and collect their outputs when done.
- ▌ Env Management 4 · grandameniumYou need to add a new API key to the system, update an existing credential, check what secrets are configured for the org or a specific agent, onboard a new third-party tool that needs credentials, diagnose why an agent cannot access a service because a key appears missing, rotate a compromised or expired key, or restart affected agents after a credential change. This skill covers the full lifecycle of environment variables and secrets in cortextOS.
- ▌ Knowledge Base 4 · grandameniumYou are about to research a topic, answer a factual question about the org, or look up context about a person, project, or tool. Before searching the web or asking the user, query the knowledge base first — the answer may already exist from a previous research session. After you complete any substantial research, ingest your findings so future agents do not repeat the same work. The KB is the org's shared memory across all agents.
- ▌ Soul Philosophy 4 · grandameniumFull behavioral philosophy for cortextOS agents - detailed principles, examples, and guidelines. Use when you need deep context on behavioral expectations or are onboarding.
- ▌ Activity Channel 3 · grandameniumYou have completed something significant and want the whole org — all agents and the user — to know about it. Or you need to broadcast a status update, a briefing summary, or a coordination announcement that is not directed at one specific agent. Use this skill any time the audience is the entire org rather than a single person or agent.
- ▌ Tool Registration 3 · grandameniumA new tool has been added to the system and is not yet documented — agents do not know it exists or how to use it. This includes any new bus script, CLI binary, MCP server, external web tool or API wrapper, or any other capability an agent can invoke. You need to add it to TOOLS.md with its command, purpose, key flags, and usage examples. Or you have discovered that TOOLS.md is out of sync with what is actually available. This keeps the tool reference current so every agent can discover and use new capabilities.
- ▌ System Diagnostics 3 · grandameniumSomething in the system feels stuck or wrong — tasks are not moving, an agent has gone quiet, goals have not been updated in days, or the orchestrator has asked for a system health report. You need to run a structured check: stale tasks, stale goals, overdue human tasks, fleet heartbeat status, and metrics. This is your diagnostic toolkit. Run it on every heartbeat (orchestrator) and whenever something seems off.
- ▌ Cron Management 6 · grandameniumManage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json — they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.
- ▌ Comms 3 · grandameniumA message has just arrived in your session from the fast-checker daemon — you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.
- ▌ Tasks 3 · grandameniumYou are about to start any meaningful piece of work — a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.
- ▌ Memory 2 · grandameniumYou need to write or update memory. This happens at session start, heartbeat, session end, or when you learn something worth keeping. Memory is how you maintain continuity across restarts and context compactions — without it, every session starts blind.
- ▌ Delegation Matrix 2 · grandameniumOrchestrator/agent/Codex delegation matrix. Reference this when scoping a task to determine who owns what. Covers three Codex modes: reviewer-only (default), implementer+reviewer, and no Codex.
- ▌ Approvals 3 · grandameniumYou are about to take an action that affects the outside world, cannot be undone, or involves real people — and you have not yet received explicit permission. This includes: sending any email or message to a real person, deploying code to production, posting on social media, making a purchase or financial commitment, deleting files or data, merging a PR to main, or publishing anything publicly. Stop, create an approval, block your task, and notify the user. Do not proceed until you receive the approval decision in your inbox.
- ▌ Heartbeat 4 · grandameniumYour heartbeat cron has fired and you need to update your status so the dashboard shows you as alive. Or you are checking whether another agent is responsive before sending them work. Or an agent appears offline or stale in the dashboard and you need to investigate whether their session is still running. A dead heartbeat means the system thinks you are down — update it proactively and check fleet health on every heartbeat cycle.
- ▌ Cron Management 7 · grandameniumManage persistent recurring scheduled tasks via the cortextos bus. Crons are stored in crons.json, loaded and dispatched by the daemon, and survive agent restarts. Use this skill for all cron CRUD: create, update, remove, list, test-fire, and inspect execution history. Never use CronCreate or /loop for persistent recurring work — those are session-only and die on restart.
- ▌ Auto Skill 3 · grandameniumYou just completed a complex task that required 8+ distinct tool calls, or you noticed you are solving the same type of problem for the third time. Create a skill candidate draft so this workflow can be reused in future sessions without rediscovery. Draft goes to skills/drafts/ — never auto-activates until the user approves.
- ▌ Onboarding 6 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ Human Tasks 3 · grandameniumYou have hit a blocker that is not a permission issue — it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.
- ▌ M2c1 Worker 5 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Autoresearch 6 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Bus Reference 5 · grandameniumComplete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.
- ▌ Event Logging 3 · grandameniumYou have just completed a task, started a session, dispatched work to another agent, finished a research cycle, or taken any significant action — and you need to record it so the dashboard activity feed shows your work. Without logging, you are invisible. Every session start, task completion, and major coordination action must produce at least one event. If you have been active but see no events in the dashboard, you have been logging nothing.
- ▌ Worker Agents 2 · grandameniumYou have a task that would benefit from running in a separate isolated Claude Code session — either because it is long-running and you do not want it to consume your context window, or because you want multiple pieces of work running in parallel that each require a full Claude Code session with its own tools, memory, and context (not just a subagent call). You will spawn one or more ephemeral worker sessions, give each a focused task, monitor their progress via the bus, and collect their outputs when done.
- ▌ Env Management 3 · grandameniumYou need to add a new API key to the system, update an existing credential, check what secrets are configured for the org or a specific agent, onboard a new third-party tool that needs credentials, diagnose why an agent cannot access a service because a key appears missing, rotate a compromised or expired key, or restart affected agents after a credential change. This skill covers the full lifecycle of environment variables and secrets in cortextOS.
- ▌ Knowledge Base 3 · grandameniumYou are about to research a topic, answer a factual question about the org, or look up context about a person, project, or tool. Before searching the web or asking the user, query the knowledge base first — the answer may already exist from a previous research session. After you complete any substantial research, ingest your findings so future agents do not repeat the same work. The KB is the org's shared memory across all agents.
- ▌ Soul Philosophy 3 · grandameniumFull behavioral philosophy for cortextOS agents - detailed principles, examples, and guidelines. Use when you need deep context on behavioral expectations or are onboarding.
- ▌ Activity Channel 2 · grandameniumYou have completed something significant and want the whole org — all agents and the user — to know about it. Or you need to broadcast a status update, a briefing summary, or a coordination announcement that is not directed at one specific agent. Use this skill any time the audience is the entire org rather than a single person or agent.
- ▌ Tool Registration 2 · grandameniumA new tool has been added to the system and is not yet documented — agents do not know it exists or how to use it. This includes any new bus script, CLI binary, MCP server, external web tool or API wrapper, or any other capability an agent can invoke. You need to add it to TOOLS.md with its command, purpose, key flags, and usage examples. Or you have discovered that TOOLS.md is out of sync with what is actually available. This keeps the tool reference current so every agent can discover and use new capabilities.
- ▌ System Diagnostics 2 · grandameniumSomething in the system feels stuck or wrong — tasks are not moving, an agent has gone quiet, goals have not been updated in days, or the orchestrator has asked for a system health report. You need to run a structured check: stale tasks, stale goals, overdue human tasks, fleet heartbeat status, and metrics. This is your diagnostic toolkit. Run it on every heartbeat (orchestrator) and whenever something seems off.
- ▌ Guardrails Reference 5 · grandameniumFull red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
- ▌ Heartbeat 5 · grandameniumYour heartbeat cron has fired and you need to update your status so the dashboard shows you as alive. Or you are checking whether another agent is responsive before sending them work. Or an agent appears offline or stale in the dashboard and you need to investigate whether their session is still running. A dead heartbeat means the system thinks you are down — update it proactively and check fleet health on every heartbeat cycle.
- ▌ Auto Skill 4 · grandameniumYou just completed a complex task that required 8+ distinct tool calls, or you noticed you are solving the same type of problem for the third time. Create a skill candidate draft so this workflow can be reused in future sessions without rediscovery. Draft goes to skills/drafts/ — never auto-activates until the user approves.
- ▌ Onboarding 7 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ M2c1 Worker 6 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Autoresearch 7 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Bus Reference 6 · grandameniumComplete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.
- ▌ Cron Management 8 · grandameniumManage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json — they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.
- ▌ Agent Management 8 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Cortext Self Diagnosis 2 · grandamenium bundleDiagnose cortextOS itself when the framework misbehaves — an agent has gone silent or wedged, agents are crash-looping, Telegram or agent-to-agent messages are not arriving, crons did not fire, an agent re-onboards or shows offline when it is running, the daemon died, or the whole fleet is down. Walks a structured evidence-first investigation across logs, the message bus, state markers, and daemon output, then classifies the finding as local config vs. a genuine framework bug — and for real bugs, drives a fix branch, a user-run test matrix, a PII/focus gate, and an upstream PR. Use this whenever someone asks you to debug, investigate, troubleshoot, or explain anything about cortext/cortextOS behavior, even casually ("why did my agent stop replying", "is something broken", "cortext is acting weird"). For stale tasks, stale goals, or workload health instead, use system-diagnostics.
- ▌ Guardrails Reference 6 · grandameniumFull red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
- ▌ Comms 2 · grandameniumA message has just arrived in your session from the fast-checker daemon — you see a block starting with === TELEGRAM or === AGENT MESSAGE. Read it, decide what action to take, and reply using the command shown in the message header. If it is from the user, they are waiting for your response right now. If it is from another agent, they may be blocked on your reply. Handle all messages before returning to other work.
- ▌ Cron Management 2 · grandameniumManage persistent recurring scheduled tasks via the cortextos bus. Crons are stored in crons.json, loaded and dispatched by the daemon, and survive agent restarts. Use this skill for all cron CRUD: create, update, remove, list, test-fire, and inspect execution history. Never use CronCreate or /loop for persistent recurring work — those are session-only and die on restart.
- ▌ Tasks 2 · grandameniumYou are about to start any meaningful piece of work — a research task, a build, a draft, a deployment, anything with a deliverable. Before you begin, create a task. During the work, mark it in_progress and write WORKING ON to daily memory. When done, complete it with a result summary and log a task_completed event. If you are blocked, set the task to blocked with the reason. If a human needs to do something first, assign it to them. Without a task, your work is invisible to the dashboard and the user.
- ▌ Heartbeat 2 · grandameniumYour heartbeat cron has fired and you need to update your status so the dashboard shows you as alive. Or you are checking whether another agent is responsive before sending them work. Or an agent appears offline or stale in the dashboard and you need to investigate whether their session is still running. A dead heartbeat means the system thinks you are down — update it proactively and check fleet health on every heartbeat cycle.
- ▌ Onboarding 2 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ M2c1 Worker 2 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Approvals 2 · grandameniumYou are about to take an action that affects the outside world, cannot be undone, or involves real people — and you have not yet received explicit permission. This includes: sending any email or message to a real person, deploying code to production, posting on social media, making a purchase or financial commitment, deleting files or data, merging a PR to main, or publishing anything publicly. Stop, create an approval, block your task, and notify the user. Do not proceed until you receive the approval decision in your inbox.
- ▌ Autoresearch 2 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Onboarding 3 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ Theta Wave 2 · grandameniumSystem-level deep improvement cycle. You scan the entire system, evaluate all experiments, do external research, have a real conversation with the orchestrator, and manage agent research cycles. Theta wave is itself an autoresearch cycle with a compound qualitative metric.
- ▌ Human Tasks 2 · grandameniumYou have hit a blocker that is not a permission issue — it is a capability issue. You genuinely cannot complete the next step because it requires a human: making a payment, entering credentials for a service you cannot access, physical action, a decision that only the user can make, or anything else outside your capabilities. You need to create a clear [HUMAN] task with step-by-step instructions, block your own work on it, and notify the orchestrator so this surfaces in the next briefing.
- ▌ M2c1 Worker 3 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Autoresearch 3 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Cron Management 3 · grandameniumManage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json — they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.
- ▌ Bus Reference 2 · grandameniumComplete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.
- ▌ Event Logging 2 · grandameniumYou have just completed a task, started a session, dispatched work to another agent, finished a research cycle, or taken any significant action — and you need to record it so the dashboard activity feed shows your work. Without logging, you are invisible. Every session start, task completion, and major coordination action must produce at least one event. If you have been active but see no events in the dashboard, you have been logging nothing.
- ▌ Upstream Sync 2 · grandameniumCheck for cortextOS framework updates from the remote repo. Fetches changes, categorizes them, explains in plain English, and applies only with user approval.
- ▌ Agent Management 2 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Env Management 2 · grandameniumYou need to add a new API key to the system, update an existing credential, check what secrets are configured for the org or a specific agent, onboard a new third-party tool that needs credentials, diagnose why an agent cannot access a service because a key appears missing, rotate a compromised or expired key, or restart affected agents after a credential change. This skill covers the full lifecycle of environment variables and secrets in cortextOS.
- ▌ Knowledge Base 2 · grandameniumYou are about to research a topic, answer a factual question about the org, or look up context about a person, project, or tool. Before searching the web or asking the user, query the knowledge base first — the answer may already exist from a previous research session. After you complete any substantial research, ingest your findings so future agents do not repeat the same work. The KB is the org's shared memory across all agents.
- ▌ Soul Philosophy 2 · grandameniumFull behavioral philosophy for cortextOS agents - detailed principles, examples, and guidelines. Use when you need deep context on behavioral expectations or are onboarding.
- ▌ Onboarding 4 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ Agent Management 3 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Autoresearch 4 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Bus Reference 3 · grandameniumComplete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.
- ▌ Morning Review 2 · grandameniumDaily morning briefing workflow. Triggered by morning cron. Pulls overnight agent work, checks goals state, cascades goals to agents, schedules tasks, sends briefing to user.
- ▌ Guardrails Reference 2 · grandameniumFull red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
- ▌ Agent Management 4 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Agent Management 5 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Guardrails Reference 3 · grandameniumFull red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.
- ▌ Cron Management 4 · grandameniumManage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json — they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.
- ▌ Agent Management 6 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Heartbeat 3 · grandameniumYour heartbeat cron has fired and you need to update your status so the dashboard shows you as alive. Or you are checking whether another agent is responsive before sending them work. Or an agent appears offline or stale in the dashboard and you need to investigate whether their session is still running. A dead heartbeat means the system thinks you are down — update it proactively and check fleet health on every heartbeat cycle.
- ▌ Auto Skill 2 · grandameniumYou just completed a complex task that required 8+ distinct tool calls, or you noticed you are solving the same type of problem for the third time. Create a skill candidate draft so this workflow can be reused in future sessions without rediscovery. Draft goes to skills/drafts/ — never auto-activates until the user approves.
- ▌ Onboarding 5 · grandameniumYou have just booted for the first time — there is no .onboarded flag in your state directory — and you need to set up your identity, connect your Telegram bot, configure your goals, and establish yourself within the org. Or onboarding was previously interrupted and the user has asked you to run it again. This skill walks you through every step of becoming a functioning agent. Do not skip steps. Do not start normal operations until onboarding is complete.
- ▌ M2c1 Worker 4 · grandameniumYou need to build software autonomously — a new project, a major feature, or any structured development task. You will act as the 'human' supervisor for a dedicated M2C1 worker session, managing it through all 12 phases: provide the brain dump, answer discovery questions, configure tools and credentials, monitor progress via bus messages and git, validate the output, and clean up when done. Use when the work is large enough to warrant a dedicated isolated build session.
- ▌ Autoresearch 5 · grandameniumThe analyst has assigned you a research cycle, or you have identified a metric you want to improve through systematic experimentation. You will form a hypothesis, make a targeted change, measure the outcome against a baseline, and decide whether to keep or discard the change. You repeat this loop until the metric improves or you exhaust viable hypotheses. This is not ad-hoc research — it is structured scientific iteration with a defined metric, a hypothesis, and a measurable result.
- ▌ Bus Reference 4 · grandameniumComplete cortextos bus CLI reference - all available commands with examples. Use when you need to look up a bus command, check syntax, or discover available tools.
- ▌ Cron Management 5 · grandameniumManage scheduled tasks (crons). Crons are daemon-managed and stored in crons.json — they survive restarts automatically. Use when: verifying crons on session start, creating new recurring tasks, updating or removing crons, troubleshooting scheduled tasks, or using the dashboard test-fire button.
- ▌ Agent Management 7 · grandameniumYou need to create a new agent, restart a crashed agent, change an agent's model or config, fix a Telegram bot token, troubleshoot why an agent is not responding, enable or disable an agent, spawn an agent for another user, manage PM2 process management, reset crash limits, or do anything that touches an agent's lifecycle, configuration, or credentials. This is the definitive guide for every agent operation in cortextOS.
- ▌ Guardrails Reference 4 · grandameniumFull red flag table with all guardrail patterns. Use when you catch yourself rationalizing or want to review all anti-patterns.