claudecodex

agent-harness

Curated review/build/test agents + secret-hardening/worktree/plan-gate hooks + supervise/wrap skills. Install once, use in every project.

2 on GitHubby joyminv0.15.4MITupdated yesterdayworkflow
/

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

This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.

What it installs

Skills (6)

  • council-review

    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. NOT a completion gate (that is /verify-completion), NOT a security audit (se

  • harness-help

    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.

  • spec

    Upstream planning-discipline — brainstorm a feature into spec.md + plan.md under .agent/plans/<slug>/, 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

  • supervise

    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 m

  • verify-completion

    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). Work

  • wrap

    Commits staged changes and opens a PR. Runs gitleaks + risk-area guards before committing. Push is user-confirmed by default; --auto-push and --auto-merge are opt-in. NOT for review or verification (run those before wrapping), and NOT when nothing has changed yet — there is nothing to commit.

Slash commands (1)

  • /agent-harness:project-init

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

Subagents (3)

  • code-reviewer

    Reviews a diff for correctness, logic, maintainability, and style. Use at wrap/PR time when the diff is review-tier tier>=1 (core/infra/review-tier.sh), or immediately when the change touches risk-area paths; also when the user says review / "check this code" / "look over" / "code review". Read-only

  • plan-checker

    Checks a written plan.md against its spec.md for decision coverage before the plan is approved. Use after /spec writes plan.md and before approval, or when the user says "check this plan" / "plan review". Read-only — recommends changes, never edits. NOT a code reviewer (that is code-reviewer), NOT f

  • security-reviewer

    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 asks for a security review of a diff, staged change, o

Hooks (30)

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" agent-session-start.sh

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-init.py

  • SessionStart

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-tier-observer.py

  • SessionEnd

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-close.sh

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-quality-gate.py

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" brain-capture.py

  • Stop

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-close.sh

  • UserPromptSubmit

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" agent-session-heartbeat.sh

  • UserPromptSubmit

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" supervisor.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" pre-tool-guard.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" loop-write-guard.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" floor-guard.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" r4-mutex-check.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" context-mode-guard.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" check-hardcoding.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" secret-content-scan.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" r4-file-mutex-check.sh

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" tdd-guard.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" spec-gate.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" loop-write-guard.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" supervisor.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" plan-scope-allow.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" floor-guard.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" secret-content-scan.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" model-routing-advisor.py

  • PreToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" council-escalation-gate.py

  • PreModelSwitch

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-tier-observer.py

  • PostModelSwitch

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" session-tier-observer.py

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" plan-gate.py

  • PostToolUse

    "${CLAUDE_PLUGIN_ROOT}/adapters/claude-code/adapter.sh" supervisor.py

View source on GitHub

More from joymin5655/Agent

All 2 plugins →

Rarely used agent-harness skills (code-tour, harness-audit, harness-loop, loop, manager-audit, persona-review, reorg-sync, worker-setup, brain-ingest, writing-critique). Optional companion to agent-harness; install with /plugin install agent-harness-extras@agent.

10 skills · 1 agent

2

Similar plugins

Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).

39 skills

mattpocock/skills 323,108

superpowers

claudecodex

Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques

15 skills · hooks

obra/superpowers 316,836

claude-mem

claudecodex

Persistent memory for Claude Code: the next session starts where the last one left off.

29 skills · 1 MCP server · hooks

thedotmack/claude-mem 116,618

mem0

claudecodex

Cross-session memory and token savings for coding agents.

6 skills · 1 agent · 1 MCP server · hooks

mem0ai/mem0 68,893

context7

claudecodex

Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.

1 MCP server

upstash/context7 64,709

Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.

5 commands

HKUDS/CLI-Anything 58,665

Maintain agent-harness?

This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.

claude & codex plugins2 plugins