joymin5655

joymin5655/Agent

Plugin Claude Code

Plugin marketplace listing 1 plugin: agent-harness.

joymin5655/Agent

Plugin Claude Code

Portable AI agent harness — curated review/build/test agents, secret-hardening + worktree + plan-gate hooks, and spec/supervise/wrap/verify-completion skills. Install once, use in every project. AI-agnostic core (Claude Code / Codex / Gemini).

joymin5655/Agent

Instructions file CodexOpenCode

Instructions for joymin5655/Agent, covering agents.md, what this repo is, operating mode for ai agents working in this repo, 1. plan before code and 2. sanitize discipline.

joymin5655/Agent

Agent

Reviews a diff for correctness, logic, maintainability, and style. Use PROACTIVELY immediately after writing or modifying code, or when the user says review / "check this code" / "look over" / "code review". Read-only — recommends changes, never writes them. Defers ALL security findings to security-reviewer (no…

joymin5655/Agent

Agent

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 / usability / copy-tone…

joymin5655/Agent

Agent

Audits diffs for OWASP Top 10, secret exposure, auth/authz bugs, injection, and unsafe crypto. Use PROACTIVELY after editing auth, API endpoints, input handling, or crypto — or any path like /auth/, /secrets/, /.env — or when the user says security / vulnerability / owasp / "secret leak". Owns ALL security findings…

joymin5655/Agent

Command

Scaffold runtime instructions, hook policy, secret scanning, and Git-hook wiring. Agents, skills, and runtime hooks come from the plugin.

joymin5655/Agent

Hook

Runs when a session starts, executing adapter.sh (3 commands). From joymin5655/Agent.

joymin5655/Agent

Hook

Runs when the agent finishes a response, executing adapter.sh (3 commands). From joymin5655/Agent.

joymin5655/Agent

Hook

Runs when you submit a prompt, before the agent sees it, executing adapter.sh (2 commands). From joymin5655/Agent.

joymin5655/Agent

Hook

Runs before the agent uses a tool for Bash, Write, Edit, MultiEdit, WebFetch, mcp__supabase__execute_sql, mcp__supabase__apply_migration, mcp__supabase__deploy_edge_function, mcp__firecrawl__firecrawl_scrape, mcp__firecrawl__firecrawl_crawl, mcp__firecrawl__firecrawl_search, mcp__firecrawl__firecrawl_extract…

joymin5655/Agent

Hook

Runs after a tool call finishes for ExitPlanMode, Task, Agent, Bash, Write, Edit and MultiEdit tool calls, executing adapter.sh (7 commands). From joymin5655/Agent.

joymin5655/Agent

Skill Claude CodeCodex

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 provenance + the…

joymin5655/Agent

Skill Claude CodeCodex

Multi-vendor code review council — runs the Claude code-reviewer agent alongside external second opinions (codex, gemini) in parallel, then synthesizes with citation verification, source tagging, and disagreement surfacing. Optionally seats grok (--with-grok) and/or an OpenRouter free-tier advisor (--with-free) as…

joymin5655/Agent

Skill Claude CodeCodex

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 for auditing a…

joymin5655/Agent

Skill Claude CodeCodex

Router over the harness skills — which skill fits your situation, and the main flow through them. NOT for performing the routed work itself — it only points; invoke the skill it names.

joymin5655/Agent

Skill Claude CodeCodex

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 skills/loop's generic mechanics. NOT for an arbitrary mission (use /loop for that), and NOT for editing…

joymin5655/Agent

Skill Claude CodeCodex

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), and NOT for…

joymin5655/Agent

Skill Claude CodeCodex

Meta-audit of a /supervise run — did the supervisor do its job? Runs the four-lane machine layer (core/infra/manager-audit.sh) over the run's logs, interprets the semantic halves, and turns actionable findings into concrete patch proposals in PROPOSALS.md for one-click user approval. Read-only analysis; NEVER applies…

joymin5655/Agent

Skill Claude CodeCodex

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 review (those are…

joymin5655/Agent

Skill Claude CodeCodex

Upstream planning-discipline — brainstorm a feature into spec.md + plan.md under .agent/plans/ /, then route to plan approval. Enforced by the spec-gate tool boundary, not prompt coercion. NOT for trivial/test/doc-only edits (the gate scopes those out), and NOT for executing an already-approved plan (that is…

joymin5655/Agent

Skill Claude CodeCodex

Dispatch a multi-wave plan to specialist agents with audit + risk-area abort. Supports --auto-push, --auto-merge, --goal-mode for budgeted runs, --verify-blocking for a hard completion-claim gate. NOT for writing the plan itself (that is /spec), and NOT for a single small edit with no waves — just make the edit.

joymin5655/Agent

Skill Claude CodeCodex

Independently re-verify a completion claim in a separate context — mechanical evidence (files/tests/assertions) plus a refute-by-default semantic judge — before a wave or task is allowed to be called "done". Emits the shared verdict schema. NOT for code-style review (that is a reviewer's lane) and NOT for verifying…

joymin5655/Agent

Skill Claude CodeCodex

Per-lane install → auth → verify onboarding for the cross-vendor worker lanes (codex, antigravity/gemini, grok, kiro) 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 probe is…