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 iCodeCraft/anti-slop --skill security-reviewgit clone --depth 1 https://github.com/iCodeCraft/anti-slopWrote 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/icodecraft/anti-slop/security-review)<a href="https://agentmods.dev/skills/icodecraft/anti-slop/security-review"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/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/icodecraft/anti-slop/security-review"><img src="https://agentmods.dev/badge/skills/icodecraft/anti-slop/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 | $0.00058 | $0.00527 |
| Opus 5 | $0.00029 | $0.00264 |
| Sonnet 5 | $0.00012 | $0.00105 |
| Haiku 4.5 | $0.00006 | $0.00053 |
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 11d 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.
What it actually says
Security Review
Review the current change like a security-minded senior. Prefer concrete findings over generic advice.
Scope
Focus on the diff and directly related call paths. Do not audit the whole repo unless asked.
Checklist
Auth & access
- Every sensitive action checks authentication and authorization
- IDs from the client are not trusted for ownership (
userIdin body ≠ proof) - Admin/debug routes are gated; no "temporary" open endpoints
Input & data
- User input is validated at the boundary (type, length, allowlist)
- SQL/NoSQL/search queries are parameterized — no string concat
- HTML/Markdown/user content is escaped or sanitized where rendered
- File uploads: size limits, type allowlist, stored outside web root, randomized names
- Path joins cannot escape intended directories (
../)
Secrets & config
- No secrets in source, logs, client bundles, or example env files with real values
- New env vars documented; defaults are safe for production
- Tokens/passwords not written to analytics or error trackers
Network & server
- Outbound fetches do not accept raw user URLs without allowlisting (SSRF)
- CORS is least-privilege; credentials only when required
- Cookies:
HttpOnly,Secure,SameSitewhere applicable
Dangerous APIs
- No
eval,dangerouslySetInnerHTML, shellexecwith unsanitized input - Deserialization of untrusted data is avoided or hardened
- Crypto/auth libraries are standard — no home-rolled JWT/crypto
Output format
Group findings:
| Severity | Rule | Where | Why it matters | Fix |
|---|---|---|---|---|
| Critical / High / Medium / Low / Note | short name | file:line or symbol |
1 sentence | concrete change |
End with:
- Blockers — must fix before merge
- Safe to ship with follow-ups — optional
If no issues: say so explicitly and list what you checked.
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.
- 11d ago First seen · 62 lines · 58 tokens per session scan A be490ec3c5ec
security-review is a skill published in the GitHub repository iCodeCraft/anti-slop (27 stars, last pushed 1mo ago), licensed MIT. It adds 58 tokens to every session and 527 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
brownfield-drift
Enforces architecture boundaries defined in PLAN.md. Use when a PR crosses module/service boundaries, when the dev asks "are we following the architecture?", or as a scheduled architecture health check. Not for querying what a module does — use brownfield-chat for that.
pr-review
Fix engine for PR review comments. Fetches review comments (Gemini bot or human), categorizes by impact, posts a prioritized fix queue, and applies fixes on dev approval. Called directly for quick fixes, or internally by pr-review-agent as part of full PR review.
standards-kit
Unified development and design standards. Enforces code quality (complexity < 8), strict naming conventions, and the mandatory use of approved UI component libraries.
module-audit-agent
Use when asked to audit a module, check its health, or assess whether it should be refactored. Runs structural query, risk check, and test generation automatically.
pr-review-agent
Full PR review orchestrator. Use when asked to review a PR or check if it is ready to merge. Runs blast radius + drift check on changed files, then hands off to pr-review for comment triage and fixes. Do NOT use pr-review directly for full reviews — use this.
vibe-coding-advisor
Inject UX principle context into your AI coding session before generating components. Maps component types (forms, tables, dashboards, navigation, checkout, etc.) to relevant UX principles, fetches their vibeCodingPrompts, and returns an assembled context block ready to paste into Cursor, Claude Code, Windsurf, or any…