Claude Code Agent Development
anthropics/claude-plugins-official
Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.
Review the current change set from an opposing harness-engineering perspective.
Install Harness Review
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install harnessworks/harness-starter-kit harness-review --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/agent-skills/skills/harness-review .claude/skills/harness-review && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .claude/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-reviewType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install harnessworks/harness-starter-kit harness-review --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/agent-skills/skills/harness-review .agents/skills/harness-review && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .agents/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install harnessworks/harness-starter-kit harness-review --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/agent-skills/skills/harness-review .cursor/skills/harness-review && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .cursor/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/harnessworks/harness-starter-kit.git --path agent-skills/skills/harness-review--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install harnessworks/harness-starter-kit harness-review --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/agent-skills/skills/harness-review .gemini/skills/harness-review && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .gemini/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install harnessworks/harness-starter-kit harness-reviewInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/agent-skills/skills/harness-review .github/skills/harness-review && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .github/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add harnessworks/harness-starter-kit --skill harness-review -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install harnessworks/harness-starter-kit harness-review --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/harnessworks/harness-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/agent-skills/skills/harness-review .opencode/skills/harness-review && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "harness-review" agent skill from https://github.com/harnessworks/harness-starter-kit/tree/main/agent-skills/skills/harness-review into .opencode/skills/harness-review/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-review", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
harness-review- GitHub stars
- 115
- Token cost
- ~276 tokens
- SKILL.md length
- 110 words
- Files
- 2
- Skills in repo
- 6
- Repo updated
- First seen
- Licence
- MIT
At a glance
Review the current change set from an opposing harness-engineering perspective.
- Works in 6 steps: Read ../../references/package-contract.md. → Read ../../references/review-workflow.md. → If… → …
- The user asks for /harness review
- SKILL.md covers Steps and Boundaries
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Harness Review is an agent skill from harnessworks/harness-starter-kit. Review the current change set from an opposing harness-engineering perspective. Use when the user asks for /harness review, /harness review sub-agent, or a no-edit harness review.
Its SKILL.md is about 280 tokens, which your agent loads only when the skill is triggered. The skill folder holds 2 other files (for example `agents/openai.yaml`).
It sits in Agent Workflows, covering Subagents. The repository describes itself as: 🐴 Prompt-first harness engineering for safer AI coding agent workflows. The licence is MIT.
When your agent uses it
- The user asks for /harness review
- /harness review sub-agent
- A no-edit harness review
Example prompts
- “/harness-review”
Workflow steps
6 steps, taken from the first numbered list in SKILL.md.
- Read ../../references/package-contract.md.
- Read ../../references/review-workflow.md.
- If ./harness-starter-kit/commands/harness-review.md exists in the target,
- Inspect the current diff and relevant harness guidance.
- If the request includes sub-agent, use a read-only reviewer subagent only
- Lead with findings by severity. If there are no actionable findings, say so
What it can do on your machine
Read from SKILL.md and the folder at commit 62437be. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md.
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Harness Review loads about 276 tokens when it runs. Until then it costs about 49 tokens; SKILL.md has 110 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from harnessworks/harness-starter-kit at commit 62437be, republished under its MIT licence (© harnessworks). 110 words, ~276 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-review/SKILL.md (or your agent's skills folder). This skill also uses 1 other file; get the full folder from GitHub.- name
- harness-review
- description
- Review the current change set from an opposing harness-engineering perspective. Use when the user asks for /harness review, /harness review sub-agent, or a no-edit harness review.
- argument-hint
- [sub-agent] [focus]
Harness Review
Challenge the current change set before completion.
Steps
- Read
../../references/package-contract.md. - Read
../../references/review-workflow.md. - If
./harness-starter-kit/commands/harness-review.mdexists in the target, prefer that canonical workflow. - Inspect the current diff and relevant harness guidance.
- If the request includes
sub-agent, use a read-only reviewer subagent only when the active runtime permits it. Otherwise fall back and report why. - Lead with findings by severity. If there are no actionable findings, say so clearly and name residual test gaps or risks.
Boundaries
- Do not modify files unless the user explicitly asks to apply fixes after the review.
- Prioritize bugs, source-of-truth risks, overreach, missing checks, stale docs, and durable-memory gaps.
© harnessworks, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
SKILL.md and 1 other file in agent-skills/skills/harness-review of harnessworks/harness-starter-kit.
- SKILL.md
- agents/openai.yaml
Open the folder on GitHubat commit 62437be
Compare with similar skills
Harness Review next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Harness Review this skillharnessworks/harness-starter-kit | 115 | — | ~276 | Automated safety check: Pass | MIT | |
| Claude Code Agent Developmentanthropics/claude-plugins-official | 38k | 7 repos | ~2.8k | Automated safety check: Pass | Apache-2.0 | |
| Subagent Driven DevelopmentAsvarox/allkaraoke | 261 | 38 repos | ~1.2k | Automated safety check: Pass | None | |
| Dispatching Parallel Agentsultralisp/ultralisp | 258 | 41 repos | ~1.5k | Automated safety check: Pass | None | |
| Reflect on Session Learningscursor/plugins | 11k | 5 repos | ~1.2k | Automated safety check: Pass | None | |
| Paseo Advisor Second Opiniongetpaseo/paseo | 20k | 1 repos | ~756 | Automated safety check: Pass | Custom licence |
Similar skills
- Official
Subagent Driven Development
Asvarox/allkaraoke
A skill your agent uses when executing implementation plans with independent tasks in the current session
Dispatching Parallel Agents
ultralisp/ultralisp
A skill your agent uses when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
- Official
Reflect on Session Learnings
cursor/plugins
Starts three parallel reviewer subagents over the current conversation transcript, then turns their findings into concrete edits to existing skills.
Paseo Advisor Second Opinion
getpaseo/paseo
Launches one separate agent through Paseo to give a second opinion on the current task, with a self-contained briefing and no permission to edit files.
Task Observer
rebelytics/one-skill-to-rule-them-all
Monitors task execution for skill improvement opportunities.
More from harnessworks/harness-starter-kit
Harness
harnessworks/harness-starter-kit
Route Harness Starter Kit workflows. An agent skill from harnessworks/harness-starter-kit.
Harness Adopt
harnessworks/harness-starter-kit
Apply Harness Starter Kit prompt-first adoption to a target repository.
Harness Doctor
harnessworks/harness-starter-kit
Run the diagnostic Harness Doctor workflow. An agent skill from harnessworks/harness-starter-kit.
Harness Refresh
harnessworks/harness-starter-kit
Review stale, duplicated, obsolete, or unused target harness guidance.
Harness Update
harnessworks/harness-starter-kit
Refresh an adopted target repository from the latest Harness Starter Kit reference.
Related
Categories
Questions about Harness Review
What does Harness Review do?
Review the current change set from an opposing harness-engineering perspective. Harness Review is an agent skill from harnessworks/harness-starter-kit. Review the current change set from an opposing harness-engineering perspective.
When should I use Harness Review?
Harness Review fits situations like: the user asks for /harness review; /harness review sub-agent; A no-edit harness review.
How do I install Harness Review in Claude Code?
Run `npx skills add harnessworks/harness-starter-kit --skill harness-review -a claude-code`. Or copy the skill folder (agent-skills/skills/harness-review in harnessworks/harness-starter-kit) into .claude/skills/harness-review in your project. Claude Code loads it when a task matches its description.
How do I install Harness Review in Codex?
Run `npx skills add harnessworks/harness-starter-kit --skill harness-review -a codex`. Or copy the skill folder (agent-skills/skills/harness-review in harnessworks/harness-starter-kit) into .agents/skills/harness-review in your project. Codex loads it when a task matches its description.
Can I use Harness Review in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add harnessworks/harness-starter-kit --skill harness-review -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/harness-review, .gemini/skills/harness-review, .github/skills/harness-review and .opencode/skills/harness-review in your project.
What does Harness Review need to run?
SKILL.md names no scripts, command-line tools or credentials: Harness Review is instructions for the agent only.
Does Harness Review access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Harness Review safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Harness Review use?
Harness Review is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Harness Review use?
About 276 tokens (SKILL.md is roughly 1.1k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Harness Review?
Skills that share tags, products or a category with Harness Review: Claude Code Agent Development (anthropics/claude-plugins-official, 38k stars), Subagent Driven Development (Asvarox/allkaraoke, 261 stars), Dispatching Parallel Agents (ultralisp/ultralisp, 258 stars) and Reflect on Session Learnings (cursor/plugins, 11k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Review?
harnessworks (a GitHub organization) maintains it in harnessworks/harness-starter-kit, which has 115 GitHub stars. The repository holds 6 skills in this directory. The repository was last updated on June 18, 2026.
Source: harnessworks/harness-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.