harness-audit

undefined-ui/second-brain-os Security Agent tooling

harness-audit is a skill in undefined-ui/second-brain-os, last changed 7 Oct 2026. It can name web addresses.

From the author

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).

What it can touch

Names web addresses

How much a skill can do, not whether it is risky.

Pattern check

Nothing flagged

That isn't proof the skill is harmless.

Commit 9173e03 · 1 Nov 2026

How the check works

Pattern check: nothing flagged

That isn't proof the skill is harmless.

Install

Each tab says whether it installs commit 9173e03, the one we checked, or the latest version.

OpenCode also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Goose also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Windsurf (Devin Desktop) also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Zed also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Roo Code also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Factory Droid also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Junie also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

Amp also looks in .agents/skills/ and ~/.agents/skills/, so use the Any agent steps.

No install command here reaches Kiro. Copy the skill's folder into .kiro/skills/ in your project, or ~/.kiro/skills/ for all your projects. undefined-ui/second-brain-os/plugins/agents-course/skills/harness-audit (opens in a new tab)

Antigravity also looks in .agents/skills/, so the Any agent steps reach it with This project. For All projects, see where Antigravity looks.

Cline also looks in .claude/skills/, so the Claude Code steps reach it with This project. For All projects, see where Cline looks.

No tab for your agent? Use Any agent for OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie and Amp. With This project, Any agent also reaches Antigravity and Claude Code reaches Cline. Kiro needs the folder copied by hand.

Pinned to commit 9173e03, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .claude/skills &&mkdir .claude/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .claude/skills/harness-audit/ &&rm -rf "$tmp"

If Claude Code was already running and this created the skills folder, run /reload-skills.

Or install the agents-course plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.

claude plugin marketplace add undefined-ui/second-brain-os --scope project &&claude plugin install agents-course@second-brain-os --scope project

Claude Code docs

Pinned to commit 9173e03, the one we checked.

Skills in the Claude apps belong to your account rather than to a project.

Make harness-audit.zip, with the skill folder at the top level:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&out="$(mktemp -d)" &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit "$out"/harness-audit &&(cd "$out" && zip -qr - harness-audit) > harness-audit.zip &&rm -rf "$tmp" "$out"

In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose harness-audit.zip.

On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.

Claude apps docs

Pinned to commit 9173e03, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .agents/skills &&mkdir .agents/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .agents/skills/harness-audit/ &&rm -rf "$tmp"

Codex picks up new skills on its own; restart it if this one does not appear.

Codex docs

Pinned to commit 9173e03, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .cursor/skills/harness-audit/ &&rm -rf "$tmp"

Cursor docs

Pinned to commit 9173e03, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .github/skills &&mkdir .github/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .github/skills/harness-audit/ &&rm -rf "$tmp"

In a running Copilot CLI session, run /skills reload.

Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.

gh skill install undefined-ui/second-brain-os plugins/agents-course/skills/harness-audit/SKILL.md@9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 --agent github-copilot --scope project

Copilot & VS Code docs

Pinned to commit 9173e03, the one we checked.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .gemini/skills/harness-audit/ &&rm -rf "$tmp"

In a running session, run /skills reload.

Or use Gemini CLI’s own installer. Installs the latest version, not the one we checked.

gemini skills install https://github.com/undefined-ui/second-brain-os.git --path plugins/agents-course/skills/harness-audit --scope workspace

Gemini CLI docs

Pinned to commit 9173e03, the one we checked.

OpenCode, Goose, Windsurf (Devin Desktop), Zed, Roo Code, Factory Droid, Junie, Amp and Antigravity read .agents/skills in a project.

From your project's root folder:

tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/undefined-ui/second-brain-os.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&git -C "$tmp" sparse-checkout set -- plugins/agents-course/skills/harness-audit &&git -C "$tmp" checkout -q 9173e03d4c40cf1a9ccd3314d0cd4194bcd7afe3 &&mkdir -p .agents/skills &&mkdir .agents/skills/harness-audit &&cp -R "$tmp"/plugins/agents-course/skills/harness-audit/. .agents/skills/harness-audit/ &&rm -rf "$tmp"

Or use the skills CLI from skills.sh. Installs the latest version, not the one we checked. The skills CLI reports installs to skills.sh unless you set DISABLE_TELEMETRY=1.

npx skills@1.7.4 add undefined-ui/second-brain-os --skill harness-audit

Agent Skills docs

Read SKILL.md first

MIT

Licence

1.2k

Repo stars

Folder last changed

Publisher

Files

Checked

1 Nov 2026

What it can touch

From the files and frontmatter at commit 9173e03. This is how much a skill can do, not whether it is risky.

Names web addresses
It mentions outside web addresses the agent may visit. We list them but don't follow them.
Outside links we did not follow

Pattern check

Pattern check: nothing flagged · commit 9173e03 · 1 Nov 2026

We checked every text file in this skill, at commit 9173e03 on 1 Nov 2026, against 45 published patterns such as download-and-run commands, hidden text and credential access. We don't run the skill, we don't read the web pages it points to, and we can't judge everything its instructions might lead an agent to do. In published tests, pattern checks like this one missed most malicious skills. Read the skill before you install it — especially anything it asks you to download or run.

How the check works Report an incorrect finding

Outside links we did not follow

https://secondbrainos.dev/#/read/course-4-harness/the-four-rings
https://secondbrainos.dev/#/read/course-4-harness/harness-practice

Format check

Each agent reads SKILL.md a little differently. We check the file against each one's published rules; we don't run the skill in any agent.

Agent Skills specPasses
The open format from agentskills.io, held to what the strictest agents enforce, so one folder loads everywhere.
- Note
  There is no license field, so readers can't tell whether they may reuse the skill. O2
  Fix: Add license: with an SPDX name such as MIT or Apache-2.0, or the name of a bundled licence file.
Claude CodePasses
Claude apps & API uploadPasses
Uploading to claude.ai or the Claude API, or packaging with Anthropic's script, accepts only the six spec fields and stops on anything else.
- Note
  The description is 415 characters. The claude.ai Help Center says 200 at most, though Anthropic's API docs and validator allow 1,024. D4
  Fix: If the claude.ai upload refuses it, trim the description to 200 characters.
OpenAI (Codex & API)Passes
VS Code & CopilotPasses

SKILL.md

Read SKILL.md on GitHub

Files

1 file

Path	Size
SKILL.md (opens in a new tab)	3.4 KB

More from undefined-ui/second-brain-os

Skill	What it can touch	Pattern check	Licence	Updated
context-auditAudit an agent's context layout against the four places: system prompt, tools, history, tail. Use when the user asks to audit, review or fix their agent's context, prompt caching, token spend per turn, or CLAUDE.md / AGENTS.md layout. Read-only: reports findings and a fix list, changes nothing. Do NOT use for writing evals (evals-bootstrap) or for loop design (goal-test). Names web addresses Pattern check: Nothing flaggedMITUpdated 7 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	7 Oct 2026
evals-bootstrapScaffold a first eval suite for an agent: mine real failures into cases, write behavioural checks over traces, and generate the runner. Use when the user wants evals, regression tests for an agent, a golden set, or asks how to know a prompt/model change did not break things. Do NOT use for a single task's done-check (goal-test) or for auditing context (context-audit). Names web addresses Pattern check: Nothing flaggedMITUpdated 7 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	7 Oct 2026
gate-checkFind 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. Use when the user asks to cut model costs or latency, says the big model handles everything, or wants a triage / routing / filter layer in front of an agent. Analysis plus an optional baseline scaffold. Do NOT use for auditing context layout (context-audit) or for building eval suites (evals-bootstrap). Names web addresses Pattern check: Nothing flaggedMITUpdated 7 Oct 2026	Names web addresses	Pattern check: Nothing flagged	MIT	7 Oct 2026
goal-testTurn 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. Use when the user wants to run an agent in a loop, asks how to know when an agent task is finished, or says a goal like "improve X" needs to become checkable. Do NOT use for building eval suites over many cases — that is evals-bootstrap. Runs shell commands +1 more Pattern check: Nothing flaggedMITUpdated 7 Oct 2026	Runs shell commands Names web addresses	Pattern check: Nothing flagged	MIT	7 Oct 2026
second-brain-backfillImport a large archive into the vault in controlled batches: triage what is worth ingesting, process oldest first, checkpoint after every batch, and keep cost visible. Use this skill whenever the user wants to import years of bookmarks, an export from another notes app, a downloads folder, a chat history dump, or says "backfill", "bulk import", "process my archive". Do NOT use for ingesting one or a few new sources, which is second-brain-ingest. Instructions only Pattern check: Nothing flaggedMITUpdated 7 Sept 2026	Instructions only	Pattern check: Nothing flagged	MIT	7 Sept 2026
second-brain-changed-my-mindTrace where the user's recorded position on something has shifted: superseded claims, contradictions between sources of different dates, and what evidence moved them. Use this skill when the user asks what they have changed their mind about, how their thinking on a topic developed, what they used to believe, or wants a quarterly look back at their own positions. Do NOT use for finding contradictions between sources with no time dimension, or for a current-state answer. Instructions only Pattern check: Nothing flaggedMITUpdated 7 Sept 2026	Instructions only	Pattern check: Nothing flagged	MIT	7 Sept 2026

All skills in undefined-ui/second-brain-os

Other Security skills

Same category, most repo stars first.

Skill	What it can touch	Pattern check	Licence	Updated
agent-architecture-auditFull-stack diagnostic for agent and LLM applications. Audits the 12-layer agent stack for wrapper regression, memory pollution, tool discipline failures, hidden repair loops, and rendering corruption. Produces severity-ranked findings with code-first fixes. Essential for developers building agent applications, autonomous loops, or any LLM-powered feature. Use when an agent or LLM feature misbehaves and the failing layer is unknown, or before shipping an agent stack. affaan-m/ECC Runs shell commands Pattern check: Nothing flaggedMITUpdated 11 Aug 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	11 Aug 2026
agent-security-hardeningSecurity hardening guidance for AI agent frameworks that process untrusted content, invoke tools, write workspace files, manage runtime identifiers, or handle credentials. Use when building or reviewing an agent runtime, autonomous worker, tool gateway, memory service, or multi-tenant agent deployment. Do not use for general web application security or offensive testing. affaan-m/ECC Instructions only Pattern check: Nothing flaggedMITUpdated 9 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	9 Oct 2026
ponytail-auditQuality audit of a whole repo: bugs, security holes, what breaks under real load, risky code without tests, slow paths, and what to delete, merge or split. Ranked, each finding explained in plain English. One-shot report, changes nothing. Use for "audit this codebase", "review the whole repo", "find bloat", "what can I delete", /ponytail-audit. DietrichGebert/ponytail Instructions only Pattern check: Nothing flaggedMITUpdated 8 Oct 2026	Instructions only	Pattern check: Nothing flagged	MIT	8 Oct 2026
csoSecurity audit: supported static findings; qualified profiles add reproduction and repair candidates. (gstack) garrytan/gstack Touches credentials +4 more Pattern check: Nothing flaggedMITUpdated 26 Oct 2026	Touches credentials Runs shell commands +3 more	Pattern check: Nothing flagged	MIT	26 Oct 2026
doubt-driven-developmentSubjects every non-trivial decision to a fresh-context adversarial review before it stands. Use when you want every assumption cross-examined before proceeding, when stress-testing a plan for hidden failure modes, when correctness matters more than speed, when working in unfamiliar code, when stakes are high (production auth, security-sensitive logic, a high-stakes migration, irreversible operations), or any time a confident output would be cheaper to verify now than to debug later. addyosmani/agent-skills Runs shell commands Pattern check: Nothing flaggedMITUpdated 28 Oct 2026	Runs shell commands	Pattern check: Nothing flagged	MIT	28 Oct 2026
security-and-hardeningHardens code against vulnerabilities. Use when auditing an input handler for vulnerabilities, when handling user input, authentication, data storage, or external integrations, or when checking a login flow is safe against the OWASP Top Ten. Use when building any feature that accepts untrusted data, manages user sessions or session cookies, or interacts with third-party services. Use when auditing dependencies for known vulnerabilities, triaging package-manager audit findings, or assessing supply-chain risk in a new package. Use when personal data or privacy compliance (GDPR, CCPA) is involved. addyosmani/agent-skills Touches credentials +3 more Pattern check: Nothing flaggedMITUpdated 30 Oct 2026	Touches credentials Runs shell commands +2 more	Pattern check: Nothing flagged	MIT	30 Oct 2026

At a glance

What it can touch

Pattern check

Install

Claude Code

Claude apps

Codex

Cursor

Copilot & VS Code

Gemini CLI

Any agent

What it can touch

Pattern check

Outside links we did not follow

Format check

SKILL.md

Files

More from undefined-ui/second-brain-os

Other Security skills