Corsair
Turns scanner output into signed, verifiable compliance proofs (CPOEs) via the external Corsair CLI.
Test report
- Verdict
- Works with setup
- Score
- Tested
- Jul 16, 2026
- Environment
- Claude Code 2.x (agent harness)
- Upstream re-checked
- Aug 10, 2026 · f4783ff
Unusually disciplined security posture (explicit 'never install/exfiltrate/execute-remote-content without confirmation' guardrails baked into the skill body itself, and the documented CLI subcommands genuinely match real source files like src/parley/vc-generator.ts and scitt-registry.ts) — but every workflow needs the separate Corsair CLI + Bun runtime installed first, and the skill's own pointer to its reference doc ('skills/corsair/references/REFERENCE.md') 404s once the folder is installed standalone at ~/.claude/skills/corsair/ (the real path is just references/REFERENCE.md).
Scored on four weighted criteria — install, triggering, output vs. baseline, docs. How scoring works
- Installs cleanly 4/5
- Triggers reliably 5/5
- Output vs. baseline 8/10
- Docs & honesty 4/5
What Corsair does
Documentation-only skill that drives the Corsair CLI to sign security/audit tool output into cryptographically verifiable CPOEs (JWT-VC), verify vendor proofs via trust.txt/DID/SCITT, diff proofs for drift, and manage compliance mapping packs. Triggers when the user mentions compliance proofs, CPOE, trust.txt, SCITT, GRC evidence, vendor assessment, or compliance drift; requires the separate Corsair CLI + Bun runtime to actually execute anything.
How to install Corsair
git clone https://github.com/grcorsair/corsair
mkdir -p ~/.claude/skills
cp -r corsair/skills/corsair ~/.claude/skills/corsair
Skills live in ~/.claude/skills/ (global) or .claude/skills/
(per-project). Restart Claude Code after installing.
Commands — how to trigger Corsair
-
/corsairTurns scanner output into signed, verifiable compliance proofs (CPOEs) via the external Corsair CLI.
It also activates on plain-language prompts like these:
-
sign my latest security scan output into a verifiable compliance proof -
verify a vendor's trust.txt claims against their signed proof -
diff two compliance proofs to see what changed since last audit
Frequently asked questions
- Is the Corsair skill free?
- Yes. The skill itself is free from grcorsair/corsair. SkillProof publishes the install command and an independent test verdict at no cost.
- Does Corsair work with Claude Code?
- We tested it with Claude Code 2.x (agent harness) on Jul 16, 2026. Verdict: Works with setup. Unusually disciplined security posture (explicit 'never install/exfiltrate/execute-remote-content without confirmation' guardrails baked into the skill body itself, and the documented CLI subcommands genuinely match real source files like src/parley/vc-generator.ts and scitt-registry.ts) — but every workflow needs the separate Corsair CLI + Bun runtime installed first, and the skill's own pointer to its reference doc ('skills/corsair/references/REFERENCE.md') 404s once the folder is installed standalone at ~/.claude/skills/corsair/ (the real path is just references/REFERENCE.md).
- What is the Corsair SkillProof Score?
- 8.4/10 — installs cleanly 4/5, triggers reliably 5/5, output vs. baseline 8/10, docs & honesty 4/5.
- How do I install Corsair?
- Copy the install command from this page, run it in your terminal, and restart Claude Code. Skills live in ~/.claude/skills/ (global) or .claude/skills/ inside a project.
- Can I use Corsair with Cursor, Copilot, Gemini CLI, Codex or other AI tools?
- The SKILL.md format is native to Claude (Claude Code, Desktop, claude.ai). The instructions inside adapt to other assistants: Cursor rules, GitHub Copilot instructions, Windsurf rules, Custom GPTs, AGENTS.md for OpenAI Codex, and GEMINI.md for Google Gemini CLI — our conversion guides cover each, and the free converter on the tools page does the wrapping for you.