signed-audit-trails-recipe
signed-audit-trails-recipe is a skill in wshobson/agents, last changed 15 Oct 2026. It can touch credentials, change agent settings, run shell commands, reach the network and name web addresses — read the findings before installing.
Step-by-step cookbook for setting up cryptographically signed audit trails on Claude Code tool calls. Use when explaining, evaluating, or demonstrating the pattern before committing to the protect-mcp runtime hooks. Covers Cedar policy, Ed25519 receipts, offline verification, tamper detection, CI/CD integration, and SLSA composition.
At a glance
What it can touch
How much a skill can do, not whether it is risky.
Pattern check
Nothing flagged
That isn't proof the skill is harmless.
Commit 7e2fb55 · 3 Nov 2026
How the check worksPattern check: nothing flagged
That isn't proof the skill is harmless.
Install
Each tab says whether it installs commit 7e2fb55, 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. wshobson/agents/plugins/signed-audit-trails/skills/signed-audit-trails-recipe (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.
Claude Code
Pinned to commit 7e2fb55, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .claude/skills &&mkdir .claude/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .claude/skills/signed-audit-trails-recipe/ &&rm -rf "$tmp"If Claude Code was already running and this created the skills folder, run /reload-skills.
Or install the signed-audit-trails plugin it ships in. Installs the latest version, not the one we checked. Installs everything in the plugin, including any hooks, MCP servers and scripts our check doesn't cover.
claude plugin marketplace add wshobson/agents --scope project &&claude plugin install signed-audit-trails@claude-code-workflows --scope projectClaude apps
Pinned to commit 7e2fb55, the one we checked.
Skills in the Claude apps belong to your account rather than to a project.
Make signed-audit-trails-recipe.zip, with the skill folder at the top level:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&out="$(mktemp -d)" &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe "$out"/signed-audit-trails-recipe &&(cd "$out" && zip -qr - signed-audit-trails-recipe) > signed-audit-trails-recipe.zip &&rm -rf "$tmp" "$out"In Claude, open Customize > Skills, select +, then + Create skill > Upload a skill, and choose signed-audit-trails-recipe.zip.
On Free, Pro and Max plans, turn on Code execution and file creation (Create and edit files in newer settings) under Settings > Capabilities.
Codex
Pinned to commit 7e2fb55, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .agents/skills &&mkdir .agents/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .agents/skills/signed-audit-trails-recipe/ &&rm -rf "$tmp"Codex picks up new skills on its own; restart it if this one does not appear.
Cursor
Pinned to commit 7e2fb55, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .cursor/skills &&mkdir .cursor/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .cursor/skills/signed-audit-trails-recipe/ &&rm -rf "$tmp"Copilot & VS Code
Pinned to commit 7e2fb55, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .github/skills &&mkdir .github/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .github/skills/signed-audit-trails-recipe/ &&rm -rf "$tmp"In a running Copilot CLI session, run /skills reload.
Or install it with gh skill, which also installs the commit we checked. Needs GitHub CLI 2.90 or later.
gh skill install wshobson/agents plugins/signed-audit-trails/skills/signed-audit-trails-recipe/SKILL.md@7e2fb559cf4b824b27f1fec49fe88f7511066d26 --agent github-copilot --scope projectGemini CLI
Pinned to commit 7e2fb55, the one we checked.
From your project's root folder:
tmp="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .gemini/skills &&mkdir .gemini/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .gemini/skills/signed-audit-trails-recipe/ &&rm -rf "$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/wshobson/agents.git --path plugins/signed-audit-trails/skills/signed-audit-trails-recipe --scope workspaceAny agent
Pinned to commit 7e2fb55, 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="$(mktemp -d)" &&git clone -q --depth 1 --filter=blob:none --no-checkout https://github.com/wshobson/agents.git "$tmp" &&git -C "$tmp" fetch -q --depth 1 origin 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&git -C "$tmp" sparse-checkout set -- plugins/signed-audit-trails/skills/signed-audit-trails-recipe &&git -C "$tmp" checkout -q 7e2fb559cf4b824b27f1fec49fe88f7511066d26 &&mkdir -p .agents/skills &&mkdir .agents/skills/signed-audit-trails-recipe &&cp -R "$tmp"/plugins/signed-audit-trails/skills/signed-audit-trails-recipe/. .agents/skills/signed-audit-trails-recipe/ &&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 wshobson/agents --skill signed-audit-trails-recipeWhat it can touch
From the files and frontmatter at commit 7e2fb55. This is how much a skill can do, not whether it is risky.
Pattern check
Pattern check: nothing flagged · commit 7e2fb55 · 3 Nov 2026
We checked every text file in this skill, at commit 7e2fb55 on 3 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 worksReport an incorrect finding
Outside links we did not follow
- https://datatracker.ietf.org/doc/draft-farley-acta-signed-receipts/
- https://www.npmjs.com/package/protect-mcp
- https://pypi.org/project/protect-mcp-adk/
- https://github.com/ScopeBlind/sb-runtime
- https://www.npmjs.com/package/@veritasacta/verify
- https://refs.arewm.com/agent-commit/v0.2
- https://veritasacta.com/attestation/decision-receipt/v0.1
- https://github.com/slsa-framework/slsa/issues/1594
- https://datatracker.ietf.org/doc/html/rfc8032
- https://datatracker.ietf.org/doc/html/rfc8785
Show 4 more
- https://docs.cedarpolicy.com/
- https://github.com/in-toto/attestation/pull/549
- https://github.com/microsoft/agent-governance-toolkit
- https://github.com/cedar-policy/cedar-for-agents
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 with warnings
The open format from agentskills.io, held to the strictest version of each rule among the agents we check.
- Warning
Paths that may not work once the skill is installed: line 10: ../../../protect-mcp/ (outside the skill folder), line 236: ../../../protect-mcp/ (outside the skill folder) and line 238: ../../../review-agent-governance/ (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- 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.
- Warning
Claude CodePasses with warnings
Claude Code reads its own extra fields, ignores unknown ones, and still loads a skill whose frontmatter is broken, without its fields.
- Warning
Paths that may not work once the skill is installed: line 10: ../../../protect-mcp/ (outside the skill folder), line 236: ../../../protect-mcp/ (outside the skill folder) and line 238: ../../../review-agent-governance/ (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
Claude apps & API uploadPasses with warnings
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.
- Warning
Paths that may not work once the skill is installed: line 10: ../../../protect-mcp/ (outside the skill folder), line 236: ../../../protect-mcp/ (outside the skill folder) and line 238: ../../../review-agent-governance/ (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Note
The description is 335 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.
- Warning
OpenAI (Codex & API)Passes with warnings
Codex finds SKILL.md by its exact name and needs a description; OpenAI's Skills API checks the frontmatter against the spec and caps uploads.
- Warning
Paths that may not work once the skill is installed: line 10: ../../../protect-mcp/ (outside the skill folder), line 236: ../../../protect-mcp/ (outside the skill folder) and line 238: ../../../review-agent-governance/ (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
VS Code & CopilotPasses with warnings
VS Code reads skills one folder below .github/skills, .claude/skills or .agents/skills and falls back to the folder name when the name is missing or differs; GitHub's Copilot docs require the exact name SKILL.md.
- Warning
Paths that may not work once the skill is installed: line 10: ../../../protect-mcp/ (outside the skill folder), line 236: ../../../protect-mcp/ (outside the skill folder) and line 238: ../../../review-agent-governance/ (outside the skill folder). B6
Fix: Use forward-slash paths relative to SKILL.md, and copy shared files into the skill.
- Warning
SKILL.md
Files
More from wshobson/agents
Other Security skills
Same category, most repo stars first.