Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add Cristhianzl/claude-skills-czl --skill security-reviewgit clone --depth 1 https://github.com/Cristhianzl/claude-skills-czlWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/cristhianzl/claude-skills-czl/security-review)<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/security-review"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/security-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/cristhianzl/claude-skills-czl/security-review"><img src="https://agentmods.dev/badge/skills/cristhianzl/claude-skills-czl/security-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00169 | $0.01035 |
| Opus 5 | $0.00084 | $0.00517 |
| Sonnet 5 | $0.00034 | $0.00207 |
| Haiku 4.5 | $0.00017 | $0.00103 |
Grade A, and why
security-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Security review
Audit the application's code for real vulnerabilities — frontend and backend — and hand back a prioritized, safe-to-apply plan. The goal is to shrink the attack surface without changing what a legitimate user sees or breaking the app.
Read first (always)
List learnings/ and read anything relevant. Reuse, don't re-derive:
- The always-on blocker set applied to every PR lives in
../reviewing-code/references/security-checks.md(PII in logs, injection, HMAC/signature, the AI-generated-code lens). Apply it — don't re-list it. - The build-time prevention rules live in
../developing-features/references/security.md(auth/session, DB least-privilege, TLS, supply chain, and the full AI/LLM guardrails) and../developing-features/references/untrusted-content.md(prompt injection). - This skill adds the OWASP-2025 breadth, the frontend / infra / privacy gaps, and the safe-remediation protocol (see
references/).
How to run a security review
- Scope it. What are you auditing — a PR, a feature, the whole app? What's the stack (framework, DB, auth provider, does it use AI)? Read
AGENTS.md/README and grep the code to map the inputs, auth checks, persistence, external calls, and any AI/LLM surface. - Go by priority, top-down (
references/owasp-2025-checklist.md): CRITICAL (secrets, broken access control / IDOR, injection, password storage) → HIGH (auth/session, security headers, CORS/CSRF, crypto, supply chain) → MEDIUM (misconfiguration, error handling, file upload, API mass-assignment, logging/alerting) → privacy (LGPD/GDPR) → continuity (backups). - Report findings — don't blind-fix. For each: severity, the exact risk, the concrete fix, and how to verify it caused no regression. Prove access-control findings (logged in as user A, try user B's resource).
- Fix under the anti-regression protocol (
references/safe-remediation.md): one change per branch/commit, backup before DB changes, test the legitimate flow before and after, report-only rollout for CSP/rate-limit, transparent re-hash for password migration, staging before prod, fail closed.
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 45 lines · 169 tokens per session scan A d627e703ab26
security-review is a skill published in the GitHub repository Cristhianzl/claude-skills-czl (5 stars, last pushed yesterday), licensed MIT. It adds 169 tokens to every session and 1,035 once invoked, about $0.0008 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
analytics-strategy
Design measurement frameworks including event taxonomy, KPI hierarchy, dashboard architecture, attribution models, and analytics implementation strategy. Use this skill whenever the user wants to plan analytics, design dashboards, build event taxonomies, define KPIs, set up tracking, or audit existing measurement.…
content-strategy
Develop a content strategy covering editorial positioning, content pillars, formats, calendar, governance, and topical authority planning. Use this skill whenever the user wants to plan a content program, define content pillars, build an editorial calendar, structure topic clusters, set up content governance, or align…
incident-response
Manage active production incidents through detection, triage, mitigation, communication, and resolution with structured roles and decision-making. Use this skill whenever the user has an active incident, a production issue, a service outage, a security incident, or needs to plan incident response procedures. Triggers…
stakeholder-communication
Communicate effectively with stakeholders across functions and seniority levels. Use this skill when writing status updates, preparing executive reviews, sharing technical decisions with non-technical audiences, managing up, communicating bad news, or designing the communication cadence for a project. Triggers on…
review-work
Post-implementation gate review: run manual QA on the real surface yourself, then launch ONE gate reviewer (never a panel) to audit goal, constraints, code quality, security, missed context, and QA evidence. Use before a PR handoff or when the user explicitly asks to review completed work.
agb-begriff-vorformuliert-305
Für AGB Begriff Vorformuliert 305: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: agb-begriff-vorformuliert-305.