Openclaw Workspace
win4r/openclaw-workspace
A skill your agent uses when maintaining or optimizing OpenClaw workspace files — AGENTS.md, TOOLS.md, SOUL.md, USER.md, IDENTITY.md, HEARTBEAT.md, BOOT.md, MEMORY.md, and related checklists and…
Audit an agent's harness against the four rings: containment, guides, sensors, permissions.
Install Harness Audit
$ npx skills add undefined-ui/second-brain-os --skill harness-audit -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install undefined-ui/second-brain-os harness-audit --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/undefined-ui/second-brain-os.git skills-src && mkdir -p .claude/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .claude/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .claude/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-auditType 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 undefined-ui/second-brain-os --skill harness-audit -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install undefined-ui/second-brain-os harness-audit --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/undefined-ui/second-brain-os.git skills-src && mkdir -p .agents/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .agents/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .agents/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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 undefined-ui/second-brain-os --skill harness-audit -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install undefined-ui/second-brain-os harness-audit --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/undefined-ui/second-brain-os.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .cursor/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .cursor/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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/undefined-ui/second-brain-os.git --path plugins/agents-course/skills/harness-audit--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 undefined-ui/second-brain-os --skill harness-audit -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install undefined-ui/second-brain-os harness-audit --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/undefined-ui/second-brain-os.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .gemini/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .gemini/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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 undefined-ui/second-brain-os harness-auditInstalls 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 undefined-ui/second-brain-os --skill harness-audit -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/undefined-ui/second-brain-os.git skills-src && mkdir -p .github/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .github/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .github/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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 undefined-ui/second-brain-os --skill harness-audit -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install undefined-ui/second-brain-os harness-audit --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/undefined-ui/second-brain-os.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/plugins/agents-course/skills/harness-audit .opencode/skills/harness-audit && 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-audit" agent skill from https://github.com/undefined-ui/second-brain-os/tree/main/plugins/agents-course/skills/harness-audit into .opencode/skills/harness-audit/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "harness-audit", 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-audit- GitHub stars
- 1k
- Token cost
- ~855 tokens
- SKILL.md length
- 398 words
- Files
- 1
- Skills in repo
- 23
- Repo updated
- First seen
- Licence
- MIT
At a glance
Audit an agent's harness against the four rings: containment, guides, sensors, permissions.
- Works in 5 steps: Ring one — containment: what can it… → Ring two — guides: what does it read… → Ring three — sensors: what fires when it… → …
- The user asks whether their agent setup is safe
- SKILL.md covers Core rule, Workflow and Output format
- Calls make
What it does
Harness Audit is an agent skill from undefined-ui/second-brain-os. Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).
Its SKILL.md is about 860 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Agent Workflows, covering Agent instruction files. The repository describes itself as: An AI second brain that maintains itself. Full guide, starter vault, agent skills and scripts for a self-organizing knowledge base in Claude Code and Obsidian. The licence is MIT.
When your agent uses it
- The user asks whether their agent setup is safe
- Wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails
- Asks what a bad session could break
- Context layout (context-audit)
Example prompts
- “/harness-audit”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Ring one — containment: what can it physically reach? Where does the
- Ring two — guides: what does it read before acting? Find CLAUDE.md /
- Ring three — sensors: what fires when it errs? Is there one command
- Ring four — permissions: what still needs a human? List what is
- Check the order. The classic smell is an inner ring doing an outer
What it can do on your machine
Read from SKILL.md and the folder at commit c7fa35b. 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
Shell commands in SKILL.md call:
make
From the folder's file list and the shell code blocks in SKILL.md.
Network
Links to these hosts (documentation or services it may open):
secondbrainos.dev
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 Audit loads about 855 tokens when it runs. Until then it costs about 107 tokens; SKILL.md has 398 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 undefined-ui/second-brain-os at commit c7fa35b, republished under its MIT licence (© undefined-ui). 398 words, ~855 tokens.
Download SKILL.mdSave it as
.claude/skills/harness-audit/SKILL.md (or your agent's skills folder).- name
- harness-audit
- description
- Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Use when the user asks whether their agent setup is safe, wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails, or asks what a bad session could break. Read-only: reports the blast radius and a hardening list, changes nothing. Do NOT use for context layout (context-audit) or cost routing (gate-check).
Audit the four rings
Theory: The four rings and Harness practice. Build from the outside in: containment, guides, sensors, permissions. The order matters because each ring must hold when every ring inside it fails — a guide can be ignored, a sensor can miss, an approval can be misclicked; a wall does not care.
Core rule
Report and rank; never harden anything yourself. The audit's one organising question is the blast radius: describe the worst session possible under the current setup and what it costs. If the user asks you to apply fixes afterwards, that is a normal edit session, not this skill.
Workflow
- Ring one — containment: what can it physically reach? Where does the agent run: the user's checkout or a worktree/container? Which credentials are in its environment — a read-only database user or the application's? Open internet or an allowlist? Real API keys or test keys? The finding is one sentence: "the worst session deletes X and spends Y."
- Ring two — guides: what does it read before acting? Find CLAUDE.md / AGENTS.md and tool descriptions. Every line should be a rule the agent can act on — flag philosophy, history, and anything over roughly a page. Flag missing rules for the repo's real landmines (migrations, generated files, deploy scripts).
- Ring three — sensors: what fires when it errs? Is there one command
(
make checkor equivalent) that runs tests, linter and types? Does the harness run it automatically after edits — a hook — or does correctness depend on the model remembering? A sensor the model must invoke voluntarily is a guide, not a sensor. - Ring four — permissions: what still needs a human? List what is auto-approved. The irreversible set — push to main, deploy, spend, delete data, send messages — should need a person; everything reversible inside the walls should not. Flag both failure modes: irreversible actions auto-approved, and reversible ones prompting so often the user rubber-stamps (approval fatigue is a hole in this ring, not a virtue).
- Check the order. The classic smell is an inner ring doing an outer ring's job: a prompt line saying "never touch prod" where a credential should have been removed. Rules in guides that could be walls belong in ring one.
Show full SKILL.md (31 more words)Show less
Output format
Harness audit — <project>
blast radius: <the worst session in one sentence>
ring 1 containment <held | open> <finding>
ring 2 guides <held | open> <finding>
ring 3 sensors <held | open> <finding>
ring 4 permissions <held | open> <finding>
Hardening list, outermost first:
1. ...Rank fixes outside-in — a wall before a better prompt, a sensor before a politer rule. Close by restating the blast radius as it would be after fix 1 alone.
© undefined-ui, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in plugins/agents-course/skills/harness-audit of undefined-ui/second-brain-os.
Open the folder on GitHubat commit c7fa35b
Compare with similar skills
Harness Audit 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 Audit this skillundefined-ui/second-brain-os | 1k | — | ~855 | Automated safety check: Pass | MIT | |
| Openclaw Workspacewin4r/openclaw-workspace | 288 | — | ~2.4k | Automated safety check: Pass | None | |
| Clawmemyoloshii/ClawMem | 210 | — | ~7.5k | Automated safety check: Pass | MIT | |
| AI Bomcdxgen/cdxgen | 1.1k | — | ~2.5k | Automated safety check: Pass | Apache-2.0 | |
| Docs Gardeningmhmzdev/the-holy-quran-app | 889 | — | ~1.1k | Automated safety check: Pass | MIT | |
| Create SkillPINA-org/PINA | 797 | — | ~1.8k | Automated safety check: Pass | MIT |
Similar skills
Clawmem
yoloshii/ClawMem
ClawMem operational reference for agents at query time — the 3-rule escalation gate, MCP tool routing, the 4 query-optimization levers, pipeline behavior (query vs intentsearch), composite scoring…
AI Bom
cdxgen/cdxgen
Generates AI-BOM, MCP inventory, AI skill inventory, and AI authorship provenance documents with cdxgen, cataloging models, inference services, Hugging Face purls, MCP servers and their…
Docs Gardening
mhmzdev/the-holy-quran-app
Audit and maintain The Holy Qur'an app's knowledge base (AGENTS.md, .agents/rules/, docs/ OKF bundle) for staleness, broken cross-links, drift from code, and OKF structural issues.
Create Skill
PINA-org/PINA
Create, modify, and improve PINA skills. An agent skill from PINA-org/PINA.
Caveman Learn Token Fixes
JuliusBrussee/caveman
Acts on a Caveman learn report: reviews ranked token sinks, applies cost-lowering edits one at a time with your consent, and reports what each fix returned.
More from undefined-ui/second-brain-os
All 23 skills in this repoGoal Test
undefined-ui/second-brain-os
Turn a vague task into a testable definition of done and generate an executable goal-test script for it, optionally with a bounded retry loop around a headless agent.
Context Audit
undefined-ui/second-brain-os
Audit an agent's context layout against the four places: system prompt, tools, history, tail.
Evals Bootstrap
undefined-ui/second-brain-os
Scaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner.
Gate Check
undefined-ui/second-brain-os
Find the decisions in a pipeline that do not need the expensive model and propose the gate for each: a rule, a classic classifier, or a small model, with fail-closed routing.
Second Brain Chat Import
undefined-ui/second-brain-os
Triage an exported chat history into what to ingest, what to archive and what to delete, with a privacy pass first.
Second Brain Graph
undefined-ui/second-brain-os
Analyse the vault's link graph and report on its shape: orphan rate, average degree, components, hubs, bridges and clusters, with what each number means for retrieval.
Related
Questions about Harness Audit
What does Harness Audit do?
Audit an agent's harness against the four rings: containment, guides, sensors, permissions. Harness Audit is an agent skill from undefined-ui/second-brain-os. Audit an agent's harness against the four rings: containment, guides, sensors, permissions.
When should I use Harness Audit?
Harness Audit fits situations like: the user asks whether their agent setup is safe; wants a review of sandboxing / permissions / hooks / AGENTS.md guardrails; asks what a bad session could break; context layout (context-audit).
How do I install Harness Audit in Claude Code?
Run `npx skills add undefined-ui/second-brain-os --skill harness-audit -a claude-code`. Or copy the skill folder (plugins/agents-course/skills/harness-audit in undefined-ui/second-brain-os) into .claude/skills/harness-audit in your project. Claude Code loads it when a task matches its description.
How do I install Harness Audit in Codex?
Run `npx skills add undefined-ui/second-brain-os --skill harness-audit -a codex`. Or copy the skill folder (plugins/agents-course/skills/harness-audit in undefined-ui/second-brain-os) into .agents/skills/harness-audit in your project. Codex loads it when a task matches its description.
Can I use Harness Audit 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 undefined-ui/second-brain-os --skill harness-audit -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-audit, .gemini/skills/harness-audit, .github/skills/harness-audit and .opencode/skills/harness-audit in your project.
What does Harness Audit need to run?
Going by SKILL.md and its folder, Harness Audit needs the command-line tools its instructions call (make).
Does Harness Audit access the network?
SKILL.md names 1 domain. As links in the text: secondbrainos.dev. This is read from the text; nothing was executed.
Is Harness Audit 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 Audit use?
Harness Audit 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 Audit use?
About 855 tokens (SKILL.md is roughly 3.4k 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 Audit?
Skills that share tags, products or a category with Harness Audit: Openclaw Workspace (win4r/openclaw-workspace, 288 stars), Clawmem (yoloshii/ClawMem, 210 stars), AI Bom (cdxgen/cdxgen, 1.1k stars) and Docs Gardening (mhmzdev/the-holy-quran-app, 889 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Harness Audit?
undefined-ui (a GitHub user) maintains it in undefined-ui/second-brain-os, which has 1,009 GitHub stars. The repository holds 23 skills in this directory. The repository was last updated on October 7, 2026.
Source: undefined-ui/second-brain-os on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.