Alibi — Development skill for Claude Code
Did the tests actually run on this code.
How to install Alibi
Installs to ~/.claude/skills/codegobrrrr9-alibi-alibi/SKILL.md
mkdir -p ~/.claude/skills/codegobrrrr9-alibi-alibi && curl -fsSL https://raw.githubusercontent.com/codegobrrrr9/alibi/HEAD/commands/alibi.md -o ~/.claude/skills/codegobrrrr9-alibi-alibi/SKILL.md Restart Claude Code, or start a new session, for it to be picked up.
What Alibi does
description: Did the tests actually run on this code? Prints the alibi verdict (VALID / STALE / FAILED / MISSING / TAMPERED) for the newest receipt and what to do about it. allowed-tools: Bash(node:*), Read
Report the alibi status for this project.
- Run
node ${CLAUDE_PLUGIN_ROOT}/skills/alibi/scripts/alibi.js verify lastfrom the project root (if that path does not exist, findalibi.jsunder the installed alibi skill directory). Pass through any arguments the user gave: $AR
Alternatives in Development
- Battle — Head-to-head graded battle card between two sites — eight dimensions, bar-by-bar, verdict line 3.6k ★
- Projectmem — Open-source coding agent memory 766 ★
- Engage.Crash — Crash → root cause → reachability → empirical exploitability verdict (native bugs) 348 ★
Full documentation available on GitHub
View Source RepositoryRelated Skills
Scvd Store X402 Verification
Check an x402 endpoint before paying it, and check the receipt after. Free instruments first; a paid signed ob
Verdict
End the cross-examination and render the verdict. PASSED only if every objection was resolved; otherwise FAILE
Refresh Usage Evidence
Bring a silo's usage evidence current when it is missing or stale, so the rota gateway and handoff planner sto
Setup Project Health
Read-only report on whether this repo's /setup-project artifacts have drifted or gone stale. Dead files, budge
Prove
Seam check. Read the ticket's seam report; re-run the pass only if it is missing or stale.
Warden Cost
Dollar accounting — what does each active rule actually save, in money? Translates the token-measured verdict
Related Agents
Evidence Auditor
Read-only audit of evidence provenance. Use when a receipt, a gate verdict, a test result, a rehearsal identif
Edc Reality Tester
EDC sub-agent. Tests whether proposed documentation or API changes would actually improve AI assistant behavio
Completion Verifier
Meticulous completion verification specialist that rigorously verifies whether claims about task completion ar