harness-review
Engine-neutral wrapper for running the read-only external review (codex, claude, or custom engine) of local git state and recording the result in the active…
Skill by bd-makers
Chalk Labs
Need help deploying harness-review?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/bd-makers-harness-review
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity, agent-building
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/harness-review
What's inside
- Skill name
harness-review- Description
- Engine-neutral wrapper for running the read-only external review (codex, claude, or custom engine) of local git state and recording the result in the active task artifact. Use when the user asks for /harness-review, harness review, external code review, or a review of current changes with a specific engine.
- License
- MIT
- Instructions
- 19 lines in SKILL.md · view on GitHub
Files (2)
- SKILL.md
- openai.yaml · agents/
SKILL.md (first lines)
# Harness Review
Use this skill as the Codex equivalent of Claude Code `/harness-review`.
## Source of Truth
- Read `../../commands/harness-review.md` before acting.
- Follow that command contract, plus `AGENTS.md` review protocol and active task docs when present.
- The engine runner table in that command is the single source for how each engine
(codex, claude, custom) is invoked — do not depend on other plugin internals.
- When no engine argument is given, apply the probe fallback chain defined in that
command with `command -v` (the command document is the single source of the order).
- Translate Claude-only references for Codex:
- `${CLAUDE_PLUGIN_ROOT}` means this installed plugin root or this repository root.
- Bash background execution means running the review without blocking and collecting the output afterwards.
- Record results in the active task's artifact `## Reviews` section with a date and the engine that ran; an unrecorded review counts as not done. If this session cannot write files (read-only reviewer context), output the dated review block verbatim so the driving session can append it instead.
- Review-only: report findings and stop. Do not fix, commit, or patch unless the user explicitly asks afterwards.From bd-makers/team-harness, MIT.
More from bd-makers/team-harness
- 0.587score
harness-codex-sim
bd-makers
Run Codex headless L5 harness simulations with `tests/sim/codex-agentloop.mjs`.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-loop
bd-makers
Codex wrapper for the optional default implementation loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-ship
bd-makers
Codex wrapper for the pre-PR final documentation pass.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-diagram
bd-makers
Harness adapter for the active task's spec/plan diagram — generates or refreshes the one diagram artifact for the current harness task under the docs user…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-sim
bd-makers
설치된 하네스와 에이전트 워크플로우 스킬(`/harness-unittest`·`/harness-comptest`)이 진짜 작동하는지 실제 claude -p 에이전트 세션으로 검증하고(L5 agent-in-the-loop) 날짜 리포트를 남긴다.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-init
bd-makers
Codex wrapper for scaffolding the Harness AIjient Team workflow into the current project.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-interview
bd-makers
Codex wrapper for Socratic spec clarification on the active task.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-inttest
bd-makers
Codex wrapper for writing Khorikov Part III integration tests in JS/TS backend projects.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-migrate
bd-makers
Codex wrapper for migrating older harness layouts to the current structure.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-observe
bd-makers
Codex wrapper for the harness observability scorecard and trip wires.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-promote
bd-makers
Codex wrapper for promoting a task artifact Learnings entry into .claude/rules with a provenance marker.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-retro
bd-makers
Codex wrapper for appending learnings to the active task artifact.
SkillAFreshness: A★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Sep 3, 2026 (1 month ago)
- Last release
- Oct 17, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/bd-makers/team-harness
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from bd-makers
- 0.587score
harness-loop
bd-makers
Codex wrapper for the optional default implementation loop.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-ship
bd-makers
Codex wrapper for the pre-PR final documentation pass.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-codex-sim
bd-makers
Run Codex headless L5 harness simulations with `tests/sim/codex-agentloop.mjs`.
SkillAFreshness: A★ 1Claude Code +9 - 0.587score
harness-diagram
bd-makers
Harness adapter for the active task's spec/plan diagram — generates or refreshes the one diagram artifact for the current harness task under the docs user…
SkillAFreshness: A★ 1Claude Code +9 - 0.584score
harness-sim
bd-makers
설치된 하네스와 에이전트 워크플로우 스킬(`/harness-unittest`·`/harness-comptest`)이 진짜 작동하는지 실제 claude -p 에이전트 세션으로 검증하고(L5 agent-in-the-loop) 날짜 리포트를 남긴다.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
harness-contrarian
bd-makers
Codex wrapper for challenging active task assumptions.
SkillAFreshness: A★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get harness-review running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
harness-review skill. Agent Mart. https://agentmart.dev/skills/bd-makers-harness-review (last updated 2026-10-24)