agent-harness-extras

Plugin agent-harness-extras from marketplace agent in joymin5655/Agent. Commands read from the repo's manifest — yesterday.

Skills (10)

• brain-ingest

  Distills quarantined raw/ session captures into curated typed atomic notes in the brain's notes/, enforcing dedup, >=2 typed edges, provenance, and a lint=0 gate, then promotes evergreen notes to the human vault via /wiki-ingest. NOT for hand-writing straight into notes/ or the vault (that bypasses

• code-tour

  Write a human reading path through a codebase or a just-finished build — one tour file with the stack, file-role rules, an ordered reading path along one real user-visible flow, safe hands-on experiments, run steps and a glossary, every path cited and checked. The source tree is never modified. NOT

• harness-audit

  Agent-driven, read-only self-audit of the harness — run the machine integrity layer once as a dry-run, present a per-check pass/fail table, cite the P1-1 doc-reality result, and for any failure give root-cause + fix + backlog follow-up. Consumes the machine gates; it does not reimplement them. NOT f

• harness-loop

  The §5 autonomous-improvement-loop procedure specialized to this harness's own reviewer prompts (agents/code-reviewer.md + agents/security-reviewer.md) — the mission-specific 9-step regulation layered on extras/skills/loop's generic mechanics. NOT for an arbitrary mission (use /loop for that), and N

• loop

  Run a mission as a bounded series of fresh-context, one-task-per-turn attempts against core/infra/loop-run.sh — hard attempt cap, per-attempt timeout, and a circuit-breaker on repeated GATE failures, resumable after a restart from on-disk state. NOT for a single one-off task (just do it directly), a

• manager-audit

  Meta-audit of a /supervise run — did the supervisor do its job? Runs the machine layer (core/infra/manager-audit.sh: four run lanes, plus a fifth review-completeness lane under --global) over the run''s logs, interprets the semantic halves, and turns actionable findings into concrete patch proposals

• persona-review

  Seat a panel of real-distribution-grounded Korean citizen personas in front of a piece of UX, copy, or content and report how ordinary users would react. Samples 5 personas from a catalog, dispatches each as an independent panelist, and synthesizes their reactions. NOT a code/security/performance re

• reorg-sync

  Sweep orphaned absolute-path references after a directory move — given an old and a new path prefix, find and optionally rewrite the five reference classes that silently break on a reorg (shebangs, git worktree pointers, crontab commands, doc anchors, and the path-keyed native-memory dir). Dry-run b

• worker-setup

  Per-lane install → auth → verify onboarding for the cross-vendor worker lanes (codex, antigravity/gemini) with a cost-model/tier briefing before anything is installed. NOT a dispatcher (`core/infra/call-worker.sh` is), and NOT a paid probe run without explicit user approval — every real round-trip p

• writing-critique

  Have two other-vendor AIs (OpenAI via codex, Google via gemini) critique a new Korean document against a rubric without knowing who wrote it, then accept only evidence-backed findings, polish, proofread, check that the meaning did not drift, and log the run. With --design it reviews a plan or design

Subagents (1)

• persona-review-orchestrator

  Runs a citizen/user persona panel over a piece of UX, copy, or content — samples real-distribution-grounded Korean personas from a catalog, dispatches each as an independent panelist, and synthesizes their reactions into one report. Use for "how would ordinary users react", user-perspective / usabil

Similar plugins