zaxbyhub
- 230 skills
- 0 followers
- 529 repo stars
- 3 days ago last updated
- ▌ Swarm · zaxbyhub bundleCodex adapter for enabling a higher-rigor swarm-like workflow in the current Codex thread. Use when the user asks for swarm mode, maximum quality, parallel investigation, extra review rigor, or a swarm-style approach without necessarily invoking the OpenCode Swarm plugin.
- ▌ Loop · zaxbyhubFull execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop command emits a [MODE: LOOP ...] signal.
- ▌ Unswarm · zaxbyhub bundleCodex adapter for disabling a previously requested swarm-like workflow in the current thread. Use when the user says unswarm, stop swarm mode, return to normal mode, simplify the workflow, or stop using extra review/delegation rigor.
- ▌ Clarify · zaxbyhubFull execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.
- ▌ Consult · zaxbyhubFull execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
- ▌ Session Retrospective · zaxbyhubAdapter (ZCode, Codex, and any harness that loads .agents/skills) for an evidence-based retrospective of the whole session, reconstructed from the harness's own session history. Use when the user asks for a retrospective, retro, or review of the session, at the end of a substantial session, or as the close-out step of a swarm-pr-feedback drive-to-merge run, merged or not. It proposes skill changes, tool fixes, and new skills or tools, each critic-reviewed before the user sees it. Analysis only.
- ▌ Session Retrospective 2 · zaxbyhubEvidence-based retrospective of an entire agent session, reconstructed from the harness's own session history (transcript, tool-call records, subagent logs), not from the current context. Reports what worked, what failed, where friction was, and proposes skill changes, tool fixes, and new skills or tools; every proposal is adjudicated by a critic before the user sees it. Analysis only: it changes no code, skills, configuration, or memory. Use when the user says "retrospective", "retro", "what went well / what didn't", "review the session", "lessons from this session", at the end of a substantial session, or as the close-out step of a swarm-pr-feedback drive-to-merge run before the memory closeout.
- ▌ Run Affected Test File In Isolation And In Co Run With I 2 · zaxbyhubrun affected test file in isolation AND in co-run with its test-suite peers after mock cleanup changes
- ▌ Swarm Pr Feedback 4 · zaxbyhubIngest an external PR review bundle (from swarm-pr-review, a human reviewer, or CI), verify each finding against current code, fix confirmed findings, add regression tests, amend the commit, and push. Use when given a structured review output with classified findings to resolve on an existing PR branch. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Research First 3 · zaxbyhubApply when planning fixes, investigating tech debt, architecting solutions, or diagnosing unknown issues. Search online for current documentation and state-of-the-art approaches before tracing through code. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Swarm Implement 4 · zaxbyhubExecute complex implementation work with a swarm-like workflow: parallel exploration, scoped planning, selective deep validation, and independent reviewer/critic checks where risk justifies them. Use for feature work, bug fixes, refactors, and multi-file changes. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Swarm Pr Review 3 · zaxbyhubRun a graph-guided, tool-augmented Swarm PR review using context packing, parallel exploration, triggered plugin micro-lanes, independent reviewer validation, critic challenge, and metrics writeback. Use for deep pull request review with low false-positive tolerance and high recall. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Writing Tests 5 · zaxbyhubRAGAPPv3 testing policy and conventions. Load before writing or modifying any test, fixing a test/CI failure, or adding coverage. Covers backend pytest + unittest (SimpleConnectionPool dependency-override harness, FK cascades, the Python 3.11-vs-local event-loop trap) and frontend Vitest + React Testing Library + jsdom (MemoryRouter, Radix Select, react-virtual mock patterns). This repo's frontend uses Vitest, NOT bun:test. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ CI Fix Monitor 3 · zaxbyhubMonitor and fix CI on an open RAGAPPv3 pull request until every required check is green. Load when asked to watch CI, diagnose red checks, or drive a PR to passing. Maps the four real CI jobs (Frontend, Backend, Quality contracts, SAST), enforces diagnose-before-fix, and covers re-push / rebase. This repo has NO dist-check, biome, bun, or per-OS matrix — ignore that guidance. Updated for PR
- ▌ Running Tests 3 · zaxbyhubRAGAPPv3 test EXECUTION patterns. Load when you need to run, scope, or diagnose tests — backend pytest and frontend Vitest — not when authoring them (see writing-tests for that). Covers per-file/-test targeting, CI-equivalent local runs, reading CI failure logs, output truncation recovery, and the Python 3.11 event-loop trap. This repo's frontend uses Vitest, NOT bun:test. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Contributing 3 · zaxbyhubEnd-to-end contribution workflow for RAGAPPv3 (KnowledgeVault). Load before creating branches, commits, or PRs. Covers branch hygiene against master, conventional commits, the four real CI gates (Frontend, Backend, Quality contracts, SAST), and where to go for publication. This repo is Python/FastAPI + npm/Vite — there is NO release-please, biome, bun, or dist-check.
- ▌ Issue Tracer 4 · zaxbyhub bundleUse when asked to trace, investigate, root-cause, plan, fix, close, or prepare a PR for a GitHub issue or bug report. Runs an evidence-first issue workflow: GitHub intake, reproduction, reasoning-guided localization, no-gap fix planning, independent critic review, user approval gate, implementation, tests, and PR-ready closure. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Design Docs 2 · zaxbyhubFull execution protocol for MODE: DESIGN_DOCS — generate or sync structured, language-agnostic design docs (domain.md, technical-spec.md, behavior-spec.md, reference/) for the project under build, with a stable section-ID registry and a design changelog. Loaded on demand by the architect when the design-docs command emits a [MODE: DESIGN_DOCS ...] signal (issue #1080).
- ▌ Phase Wrap 3 · zaxbyhubFull execution protocol for MODE: PHASE-WRAP -- phase boundary evidence, drift and hallucination gates, retrospectives, phase completion, and final council.
- ▌ QA Sweep 3 · zaxbyhubApply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Commit Pr 5 · zaxbyhubCommit, push, publish, ship, or open a GitHub pull request for ragappv3 changes. Use for PR creation, PR review follow-up pushes, draft PR updates, and release-ready local changes in this repo. Enforces ragappv3 branch hygiene, scoped staging, conventional commit titles, draft PRs against master, and Python/FastAPI plus npm/Vite validation. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Unswarm 3 · zaxbyhubDisable swarm mode for the current session and return to normal behavior. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Swarm 4 · zaxbyhubEnable a high-quality swarm-like workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing the agent runner's native speed. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Loop 2 · zaxbyhubFull execution protocol for MODE: LOOP — the compound-engineering loop: brainstorm → plan → build → review → improve, iterating under defense-in-depth stop conditions with generator/critic separation, durable resumable state, and mandatory compounding learning capture. Loaded on demand by the architect when the loop command emits a [MODE: LOOP ...] signal.
- ▌ Pr Review Database API · zaxbyhubPR review checklist for database-backed FastAPI + SQLite + React APIs. Use when reviewing changes that touch API response models, database queries, or frontend-backend data contracts.
- ▌ Config Env Contract Check 2 · zaxbyhubAudit environment and configuration contracts across backend settings, frontend env usage, Docker, Compose, CI, docs, and examples. Use when changing config, deployment, root paths, CORS, settings schemas, env examples, or Docker files. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Auth Timestamp Invalidation 2 · zaxbyhubDocument the discipline of propagating timestamp fields through token invalidation flows. Use when implementing access-token refresh reuse, password change epoch, or any token revocation flow that must invalidate outstanding tokens. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Authz Bridging Exceptions · zaxbyhubDocument two anti-patterns in the auth override branch: (a) masking non-401 HTTPExceptions when falling back to an alternative auth mechanism, and (b) using inspect.isawaitable() instead of inspect.iscoroutine() on the evaluate closure, which yields None for async def overrides. Critical for auth dependencies with JWT + service-account (SA) fallback (get_chat_stream_auth_context, get_wiki_events_auth_context, and any override branch calling get_evaluate_policy).
- ▌ Authz Bridging Exceptions 2 · zaxbyhubDocument two anti-patterns in the auth override branch: (a) masking non-401 HTTPExceptions when falling back to an alternative auth mechanism, and (b) using inspect.isawaitable() instead of inspect.iscoroutine() on the evaluate closure, which yields None for async def overrides. Critical for auth dependencies with JWT + service-account (SA) fallback (get_chat_stream_auth_context, get_wiki_events_auth_context, and any override branch calling get_evaluate_policy). Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Test Isolation Patterns 2 · zaxbyhubDocument pytest pollution patterns observed in this repo where tests pass in isolation but fail in combined sessions due to shared global state. Recommend autouse fixture scoping or explicit teardown patterns to make tests reliable in any combination. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Review Finding Validator 2 · zaxbyhubValidate external reviewer, CI, audit, swarm, or PR findings as claims before implementing or reporting them. Use when given a bundle of review findings, requested-changes comments, audit output, or suspected regressions that must be classified with evidence. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ CI Compatibility Audit · zaxbyhub bundleLightweight PR-time audit for whether changes are compatible with the actual RAGAPPv3 GitHub Actions workflow, dependency lockfiles, scripts, and cross-platform local validation.
- ▌ CI Compatibility Audit 2 · zaxbyhub bundleLightweight PR-time audit for whether changes are compatible with the actual RAGAPPv3 GitHub Actions workflow, dependency lockfiles, scripts, and cross-platform local validation. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Engineering Conventions 4 · zaxbyhubRAGAPPv3 engineering conventions — backend (FastAPI + SQLite + LanceDB), frontend (React + TypeScript + Vite + Vitest), database/migration/RBAC patterns, and the multi-agent skill layout. Load before implementing or refactoring backend routes/services/migrations or frontend pages/components, or when you need to know "how does this repo do X". Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Tech Debt CI Review 3 · zaxbyhubDeep technical debt and CI stability audit for identifying test theater, missing or mis-scoped tests, actual and potential test failures, flaky-test risk, dependency/toolchain brittleness, and structural debt that prevents PRs from going green safely. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Module Test Isolation 2 · zaxbyhubDocument the discipline of isolating module-level mutable state in tests. Use when adding tests that touch global registries, singletons, or class attributes. Prevents test pollution that surfaces only in combined pytest sessions. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Subpath Deployment · zaxbyhubRAGAPPv3 subpath/reverse-proxy deployment system. Load before touching anything related to APP_ROOT_PATH, VITE_APP_BASENAME, VITE_API_URL, cookie paths, SPA catch-all routing, proxy configuration, or Docker build args for the frontend. Contains locked architectural decisions that must not be re-litigated.
- ▌ Subpath Deployment 2 · zaxbyhubRAGAPPv3 subpath/reverse-proxy deployment system. Load before touching anything related to APP_ROOT_PATH, VITE_APP_BASENAME, VITE_API_URL, cookie paths, SPA catch-all routing, proxy configuration, or Docker build args for the frontend. Contains locked architectural decisions that must not be re-litigated. Adapter pointing to the canonical repo skill; refer to that for the full protocol.
- ▌ Phase Wrap 5 · zaxbyhubFull execution protocol for MODE: PHASE-WRAP -- phase boundary evidence, drift and hallucination gates, retrospectives, phase completion, and final council.
- ▌ Writing Tests 8 · zaxbyhubApply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces pytest framework rules, mock isolation, cross-platform compatibility (Linux, macOS, Windows), and CI pipeline awareness. Load this skill before touching any test file. For CI failure debugging specifically, also load the ci-failure-resolver skill.
- ▌ Commit Pr 7 · zaxbyhubApply when committing, pushing, opening a PR, writing a pull request, creating release notes, or updating a changelog. Enforces conventional commit format, mandatory release notes, 5-tier test suite, SHA-pinning for workflow changes, and correct PR body format.
- ▌ Swarm 6 · zaxbyhubEnable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.
- ▌ Swarm Pr Review 5 · zaxbyhubRun a swarm-like PR review using parallel exploration, independent reviewer validation, and critic challenge. Use for deep pull request review with low false-positive tolerance.
- ▌ Reviewing Code Core 2 · zaxbyhubEvidence-first code review for correctness bugs, AI-generated code smells, unsupported claims, unwired functionality, dependency hallucinations, and release-to-code mismatches.
- ▌ Reviewing Doc Drift 2 · zaxbyhubVerify that README changes, release notes, changelog bullets, migration notes, PR descriptions, examples, and docstrings match what the code actually ships.
- ▌ Reviewing Dependencies 2 · zaxbyhubValidate new and changed dependencies, imports, install commands, lockfile entries, and runtime tool assumptions for package hallucinations, slopsquatting, cross-ecosystem confusion, and version validity.
- ▌ Unswarm 4 · zaxbyhubDisable swarm mode for the current Claude Code session and return to normal behavior.
- ▌
- ▌ Contributing 4 · zaxbyhubEnd-to-end PR workflow for opencode-swarm. Covers branch setup, conventional commits, mandatory release notes, 5-tier CI checks, and PR submission format. Load this skill before creating branches, commits, or pull requests.
- ▌ Execute 4 · zaxbyhubFull execution protocol for MODE: EXECUTE -- task execution, coder retry handling, QA gates, completion evidence, and per-task closure.
- ▌ Writing Tests 7 · zaxbyhubGuidelines for writing, organizing, and maintaining tests in the opencode-swarm repository. Covers framework rules (bun:test), mock isolation, CI pipeline structure, file placement, and anti-patterns that break cross-platform CI. Load this skill before writing or modifying any test file.
- ▌ Swarm 5 · zaxbyhubEnable a high-quality swarm-like Claude Code workflow for the current session, and optionally execute a task immediately using that mode. Uses parallel subagents for breadth, independent reviewer validation for precision, and critic challenge for final confidence. Use when the user wants swarm-like behavior, higher review rigor, or maximum quality without sacrificing Claude Code speed.
- ▌ QA Sweep 4 · zaxbyhubApply when implementing features, fixing bugs, debugging errors, investigating failures, tracing root causes, reviewing tech debt, tracing issues, planning fixes, or completing any task. Enforces parallel sub-agent implementation, independent adversarial review, and a 95% confidence gate before stopping.
- ▌ Writing Tests 6 · zaxbyhubApply when writing tests, modifying test files, fixing test failures, debugging CI failures, adding test coverage, creating adversarial tests, or reviewing any file under tests/. Also apply when implementing features or fixes that require corresponding test changes. Enforces bun:test framework rules, mock isolation, cross-platform compatibility (Linux, macOS, Windows), and CI pipeline awareness. Load this skill before touching any test file.
- ▌ Swarm Pr Review 4 · zaxbyhubRun a swarm-like PR review using parallel exploration, independent reviewer validation, and critic challenge. Use for deep pull request review with low false-positive tolerance.
- ▌ Tech Debt CI Review 4 · zaxbyhubDeep technical debt and CI stability audit for identifying test theater, missing or mis-scoped tests, actual and potential test failures, flaky-test risk, dependency/toolchain brittleness, and structural debt that prevents PRs from going green safely.
- ▌ Commit Pr 6 · zaxbyhubMandatory publication protocol for the GitHub Copilot coding agent and custom Copilot agents in ragappv3. Load when assigned to an issue or when committing, pushing, opening/updating/readying a PR, or closing out remote CI. Routes to the single canonical commit-pr source of truth.
- ▌ Phase Wrap 4 · zaxbyhubFull execution protocol for MODE: PHASE-WRAP -- phase boundary evidence, drift and hallucination gates, retrospectives, phase completion, and final council.
- ▌ Deep Research 3 · zaxbyhubFull execution protocol for MODE: DEEP_RESEARCH — orchestrator-worker deep research over external sources: decompose, iterative web_search/web_fetch retrieval, parallel sme synthesis, dual-reviewer claim verification, critic challenge of high-stakes claims, and a cited report. Loaded on demand by the architect when the deep-research command emits a [MODE: DEEP_RESEARCH ...] signal.
- ▌ Subprocess Safety 2 · zaxbyhubSafe Python subprocess patterns for RAGAPPv3. Load before adding, modifying, or reviewing any code that calls subprocess.run / subprocess.Popen / asyncio.create_subprocess_exec. Covers list-form args (no shell=True with untrusted input), timeout, cwd, bounded stdout/stderr capture, returncode checks, cleanup, and the async variant. This repo's backend is Python only — ignore any Bun / Node child_process / Windows .cmd guidance.
- ▌ Swarm Pr Subscribe 4 · zaxbyhubMonitor a pull request after creation and act autonomously on pushed PR activity. Use when subscribing to a PR after opening it, when asked to watch, babysit, or autofix a PR until merge, or when a <pr-activity> wake message or [pr-monitor:...] advisory arrives for a subscribed PR. Owns event triage (fix / ask / skip), bounded-retry escalation, and terminal-state cleanup.
- ▌ Codebase Review Swarm 4 · zaxbyhub bundleRun a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Adapter pointing to the canonical opencode-swarm skill; refer to that for the full protocol.
- ▌ Codebase Review Swarm 5 · zaxbyhubRun a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Adapter pointing to the canonical opencode-swarm skill; refer to that for the full protocol.
- ▌ Codebase Review Swarm 6 · zaxbyhub bundleRun a rigorous, quote-grounded codebase review or security/QA/accessibility/performance/AI-slop/enhancement audit. Use for full-repo or large-subsystem review reports; not for normal implementation. Performs Phase 0 inventory, selected exhaustive tracks with non-diluting depth, coverage closure, reviewer/critic validation, and writes .swarm/review-v8 artifacts without modifying source files.
- ▌ Plan 2 · zaxbyhubFull execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
- ▌ Resume 2 · zaxbyhubFull execution protocol for MODE: RESUME -- continuing an existing approved plan safely from current state.
- ▌ Clarify 2 · zaxbyhubFull execution protocol for MODE: CLARIFY -- structured clarification funnel with critic review before surfacing user decisions.
- ▌ Consult 2 · zaxbyhubFull execution protocol for MODE: CONSULT -- answering advisory questions with bounded evidence and clear uncertainty.
- ▌ Council 2 · zaxbyhubFull execution protocol for MODE: COUNCIL -- General Council research, parallel member dispatch, disagreement handling, and synthesis.
- ▌ Execute 3 · zaxbyhubFull execution protocol for MODE: EXECUTE -- task execution, coder retry handling, QA gates, completion evidence, and per-task closure.
- ▌ Specify 2 · zaxbyhubFull execution protocol for MODE: SPECIFY -- spec creation, codebase reality checks, SME input, QA gate persistence, and optional council spec review.
- ▌ Discover 2 · zaxbyhubFull execution protocol for MODE: DISCOVER -- read-only repository discovery and governance/context mapping.
- ▌ Deep Dive 2 · zaxbyhubFull execution protocol for MODE: DEEP_DIVE — read-only codebase audit with parallel explorer waves, 2 independent reviewers, and sequential critic challenge for HIGH/CRITICAL findings. Loaded on demand by the architect when the deep-dive command emits a [MODE: DEEP_DIVE ...] signal.
- ▌ Brainstorm 2 · zaxbyhubFull execution protocol for MODE: BRAINSTORM -- structured discovery dialogue, approach selection, spec drafting, QA gate selection, and transition handling.
- ▌ Critic Gate 2 · zaxbyhubFull execution protocol for MODE: CRITIC-GATE -- plan critic review, revision loops, and hard stop before execution.
- ▌ Clarify Spec 2 · zaxbyhubFull execution protocol for MODE: CLARIFY-SPEC -- resolving spec clarification markers and maintaining spec/planning alignment.
- ▌ Issue Ingest 2 · zaxbyhubFull execution protocol for MODE: ISSUE_INGEST -- GitHub issue intake, localization, spec generation, and transition to planning or tracing.
- ▌ Reviewing Security 2 · zaxbyhubInspect trust boundaries, validation, authn/authz, deserialization, command execution, path handling, secrets, and failure handling with an evidence-first security review.
- ▌ Pre Phase Briefing 2 · zaxbyhubFull execution protocol for MODE: PRE-PHASE BRIEFING -- phase-start context assembly, evidence review, and task readiness checks.
- ▌ Commit Pr 3 · zaxbyhubMandatory publication protocol for the GitHub Copilot coding agent and custom Copilot agents in opencode-swarm. Load when assigned to an issue or when committing, pushing, opening/updating/readying a PR, writing release notes, or closing out remote CI. Routes to the single canonical commit-pr source of truth.
- ▌ Pr Review Fix 2 · zaxbyhub bundleLegacy compatibility entry point for PR review feedback fixes. Use swarm-pr-feedback instead for new work; this shim exists so older references still route to the canonical feedback-closure workflow.
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌
- ▌ Read Document · zaxbyhubRead and extract text from document files (.docx, .pdf, .xlsx, .pptx, .csv, .rtf, .odt, .epub, .html) into plain text or markdown for editing
- ▌ Reviewing Security · zaxbyhubInspect trust boundaries, validation, authn/authz, deserialization, command execution, path handling, secrets, and failure handling with an evidence-first security review.
- ▌ Recurring Tool Patterns · zaxbyhubCollection of frequently re-learned tool, process, and dispatch patterns that the swarm encounters across sessions. Each pattern has its own trigger, making this a multi-pattern reference rather than a single workflow.
- ▌ Csharp Cancellation Patterns · zaxbyhubApply when modifying any async method in the Adapters/ layer (FtpFileClient, SftpFileClient), the IFileClient interface, or AppBridge file-operation calls. Also apply when adding new async methods that interact with FTP/SFTP libraries or when reviewing cancellation correctness. Covers FluentFTP, SSH.NET, and SemaphoreSlim patterns specific to this codebase.
- ▌ Fastapi Rate Limiting Integration · zaxbyhubPatterns for integrating rate limiting into FastAPI applications using slowapi. Covers decorator signatures, dependency injection, and common pitfalls.
- ▌ Plan · zaxbyhubFull execution protocol for MODE: PLAN -- plan creation, external plan ingestion, QA gate persistence, task granularity, and traceability checks.
- ▌ Ship · zaxbyhub bundleOrchestrate any code change from requirements to merge-ready PR — scope-calibrated from small fixes to full features. Composes /spec, /implement, /review, and /research with depth that scales to the task: lightweight spec and direct implementation for bug fixes and config changes, full rigor for features. Use for ALL implementation work regardless of perceived scope — the workflow adapts depth, never skips phases. Triggers: ship, ship it, feature development, implement end to end, spec to PR, implement this, fix this, let's implement, let's go with that, build this, make the change, full stack implementation, autonomous development.
- ▌ Resume · zaxbyhubFull execution protocol for MODE: RESUME -- continuing an existing approved plan safely from current state.
- ▌
- ▌ Reviewing Code Core · zaxbyhubEvidence-first code review for correctness bugs, AI-generated code smells, unsupported claims, unwired functionality, dependency hallucinations, and release-to-code mismatches.
- ▌ Reviewing Doc Drift · zaxbyhubVerify that README changes, release notes, changelog bullets, migration notes, PR descriptions, examples, and docstrings match what the code actually ships.
- ▌ Module Test Isolation · zaxbyhubDocument the discipline of isolating module-level mutable state in tests. Use when adding tests that touch global registries, singletons, or class attributes. Prevents test pollution that surfaces only in combined pytest sessions.
- ▌ Reviewing Dependencies · zaxbyhubValidate new and changed dependencies, imports, install commands, lockfile entries, and runtime tool assumptions for package hallucinations, slopsquatting, cross-ecosystem confusion, and version validity.