Plugins

3 plugins

@intense-visions

Agents from Intense-Visions/harness-engineering.

100 skills · plugin

ECC from livelybug/harness-repo-skill-collection.

54 skills · plugin

Bridges to pi (dev/pi), a minimal terminal coding harness. Delegates coding tasks to the pi CLI for execution with full file and git context.

3 skills · plugin

Results for “harness”

12 skills

harness-brick-office

Build and maintain a browser-based office dashboard that visualizes .harness runtime state including missions, CXX status, hired workers, events, archive state, and ops exceptions.

dynamic-workflow-mode

Design task-local harnesses, eval gates, and reusable skill extraction for adaptive agent workflows.

spike-consumer-forked

OI-3 spike harness — heavy consumer skill, FORKED arm. Builds an incident post-mortem and sources the readability standard mid-workflow via a forked (context fork) guidance skill. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

spike-consumer-inline

OI-3 spike harness — heavy consumer skill, INLINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow via an inline (non-forked) guidance skill. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

spike-consumer-baseline

OI-3 spike harness — heavy consumer skill, BASELINE arm. Builds an incident post-mortem and sources the readability standard mid-workflow by reading a file directly, with NO Skill-tool call. Use only when explicitly invoked by the spike harness with a TRIAL_ID and data path.

More results

ai-builder-club

setup-codebase-harness

Sets up a codebase for reliable agent-driven development by making it legible (structured docs, custom lints, code graph), executable (one-command dev stack, cloud sandbox), and verifiable (e2e gate, verify-before-ship loop).

CEO/Dispatcher. Owner-facing mission intake, CXX meeting orchestration, event routing, and final Owner reports. Trigger with /goal, /submission, /hot-fix, /ceo.

deep-confidence

Deep Confidence Harness — a thinking, planning, and execution framework that forces structured reasoning before acting. Combines Monte Carlo scenario analysis, calibrated confidence, multi-perspective debate, and optimal path planning. Use before any complex decision, build, or task. Activates on: 'deep confidence', 'think before you act', 'plan first', 'Atlas mode', 'reason through this', 'what should I do', 'think this through', 'best approach', 'reason carefully', 'plan and execute'.

Orchestrate parallel AI agent sessions using dmux, a tmux pane manager for agent harnesses like Claude Code and Codex.

Provides cross-harness memory for agents by maintaining a local memex and offering commands to query, record, and check status across sessions.

project-control-loop

Audits, develops, tests, and tracks software projects through a Project Loop Harness with SQLite memory, evidence-backed status, and a generated HTML dashboard.

Mines SpecStory coding histories from any agent into a persistent corpus, surfaces reproducible workflows with corroborated evidence, and interactively forges chosen ones into skills installed across agent harnesses.