w-security — Claude Code skill: security review
w-security is a Claude Code skill that checks code changes or a repository tree against its security docs and existing checks. Run it to review a change for security defects.
MIT 647 installs ★ 1 updated 2026-10-02
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a claude-codeWhat w-security does
w-security examines changed paths for security defects and compares its findings with repository security documentation and existing scanners. It reads the security docs first. If the repository has none, it stops and asks for them rather than making up a policy.
The skill starts 2–3 read-only explorers to inspect authentication and authorization, secret exposure, and input validation. Each suspected defect needs a trigger and a consequence. By default, w-security reports findings without changing files; running checks or applying fixes requires authorization. A human must approve policy changes.
What it helps with
- find security defects in changed files
- compare code changes with repository security guidance
- inspect secret exposure and input validation
- verify the trigger and consequence of a suspected defect
Example prompts for the agent
- Review this branch's changes for security defects against the repository docs.
- Check the changed paths for authentication, secret exposure, and input validation issues.
- Run the security checks documented in the repository and report the results.
How to install w-security
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a claude-code2Manually: put the files in place
~/.claude/skills/w-security/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/w-security/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a codex2Manually: put the files in place
.agents/skills/w-security/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a cursor2Manually: put the files in place
.cursor/skills/w-security/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install blockmatic-icebox/basilic-skills skills/workflow/w-security2Manually: put the files in place
.github/skills/w-security/SKILL.md1Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a gemini-cli2Platform CLI
gemini skills install https://github.com/blockmatic-icebox/basilic-skills --path skills/workflow/w-securityManually: put the files in place
.devin/skills/w-security/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add blockmatic-icebox/basilic-skills --skill w-security -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about w-security
How do I install w-security in Claude Code?
Run npx skills add blockmatic-icebox/basilic-skills --skill w-security -a claude-code. The skill file is at ~/.claude/skills/w-security/SKILL.md.
What does w-security do?
It reviews changes or a repository tree against security documentation and existing scanners. Suspected defects need a trigger and consequence, and the default behavior is to report findings without editing files.
What does w-security need to work?
The repository needs security documentation. If it is missing, the skill stops and asks for it; running checks or making fixes also requires authorization.
Source text
SKILL.md · MIT
--- name: w-security description: Review the change or tree against repository security docs and existing checks. disable-model-invocation: true --- Find security defects relative to repository security docs and existing scanners. Do not invent CORS, encryption, password, or header policy. Stay report-only unless the user asked to fix. 1. Read the repository security docs. If missing, stop and ask; do not invent a bar. 2. Spawn 2–3 read-only explorers on authn/authz, secret/exposure, and input validation for the changed paths. Reconcile trigger and consequence yourself. 3. Validate each suspected issue with a trigger and consequence. Skip invented CVEs and timings. 4. If authorized, run existing security scripts or CI jobs from the docs or package.json. Record passed, failed, or not run. 5. If fixes are authorized, change the owning cause. Policy changes need a human. Docs: `/w-docs` if behavior or commands changed.
© blockmatic-icebox · MIT · blockmatic-icebox/basilic-skills