/precommit
Run the pre-commit security gate on the current changeset and report a single pass/fail verdict.
$ npx -y skills add jassics/awesome-claude-security --agent claude-codeHow it fires
How this command gets triggered: by you, by Claude, or both.
- Fires itselfClaude auto-loads it when your prompt matches the work.
- You can call itInvoke it directly when you want it.
- Slash command
/precommit
Context preview
What this command does when you run it.
Run the pre-commit security gate on the current changeset and report a single pass/fail verdict.
Command definition
precommit.mddescription: Run the pre-commit security gate on the current changeset and report a single pass/fail verdict. argument-hint: [optional: path/scope to check instead of the full diff]
Run the pre-commit security gate for: **$ARGUMENTS** (default: the current staged/unstaged changeset).
1. **Scope** — `git status` / `git diff --cached` (fall back to `git diff` if nothing is staged) to find changed files. Stay scoped to the diff; this is a fast pre-commit check, not a full-repo audit. 2. **Run the gate** — `/developer:pre-commit-gate` to aggregate secret/gitignore hygiene, SAST/SCA on the diff, and (if relevant) IaC and Claude-config checks into one verdict. 3. **Report** — a single **BLOCK** or **PASS** line at the top, followed by the verdict table (check · result · blocking findings). On BLOCK, give the exact fix for each blocking finding, not just the diagnosis.
For deep, multi-step coordination beyond a single commit gate (e.g. reviewing a whole new feature's security posture), hand off to the `developer` agent.
A Claude Code plugin marketplace for the full cybersecurity & GenAI-security lifecycle — from recon and threat modeling to detection engineering, GRC, and CISO-level strategy. A pentester knows which OWASP test bends a broken-access-control endpoint.
Repo: jassics/awesome-claude-security
Other commands on awesome-claude-security.
- /safety-review
Run an AI safety review for a feature/model — harms, evaluations, guardrails, and a documented safety case.
Open command - /defend
Run a threat-informed defense cycle for a technique or threat — coverage check, hunt, detection, and purple-team validation.
Open command - /board-brief
Build a board/executive security brief — strategy, quantified risk, and a board-ready deck.
Open command - /tech-review
Assess technology/security risk for a strategic decision and frame the secure-by-design path.
Open command - /assessment
Run a compliance gap-assessment for a framework, tie gaps to risk, and produce findings + remediation.
Open command - /engagement
Run an authorized penetration test end-to-end, chaining recon, testing, and reporting skills into one flow.
Open command