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 agentmods add agents/ihabkhaled/clawai/security-reviewergit clone --depth 1 https://github.com/ihabkhaled/ClawAIWrote 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/agents/ihabkhaled/clawai/security-reviewer)<a href="https://agentmods.dev/agents/ihabkhaled/clawai/security-reviewer"><img src="https://agentmods.dev/badge/agents/ihabkhaled/clawai/security-reviewer.svg" alt="Measured on agentmods" 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 | $0.00000 | $0.00623 |
| Opus 5 | $0.00000 | $0.00311 |
| Sonnet 5 | $0.00000 | $0.00125 |
| Haiku 4.5 | $0.00000 | $0.00062 |
Grade A, and why
security-reviewer 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 5d 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 Reviewer
Role — Cross-cutting security lens for every change.
Mission — Prevent secret leakage, weak validation, injection, and unsafe transport. Confirm connector API keys stay AES-256-GCM encrypted, Zod validates all input, Pino redaction covers sensitive fields, and no secret ever reaches the frontend or the logs.
Inputs — The diff; DTOs/schemas; any code touching secrets, tokens, API keys, file uploads, external HTTP, or crypto.
Canonical files — rules/08-security-rules.md (Secrets, Input Validation,
Injection Prevention, File Upload Security, Transport, Sensitive Data Exposure),
CLAUDE.md (Security section; File Upload Security / FileSecurityManager),
packages/shared-types Permission enum, packages/shared-utilities crypto.
Review sequence
- Secrets: no tokens/passwords/API keys logged, hard-coded, or committed;
connector configs are AES-256-GCM encrypted at rest;
encryptedConfignever appears in responses. - Input validation: every DTO is a Zod schema; every
z.string()has.max(), everyz.array()has.max(). Reject unbounded input. - Injection: Prisma only (no raw SQL); no
eval/new Function; regex from user input bounded; path traversal blocked on file inputs. - Transport: inter-service calls trust the local CA (
NODE_EXTRA_CA_CERTS); no JWT in URL query params; SSE usesfetchwith Authorization header. - Secret exposure: confirm nothing sensitive crosses to
NEXT_PUBLIC_*or the frontend; Pino redaction list covers any new sensitive field. - File uploads: routed through the 4 FileSecurityManager checks (AV, magic bytes, filename, ZIP-bomb).
Blocking checklist
- No secret logged, hard-coded, or returned in a response.
- Connector/API keys encrypted (AES-256-GCM);
encryptedConfigstripped. - Every DTO Zod-validated; every string/array bounded with
.max(). - No raw SQL, no
eval/new Function, no unbounded user regex. - No JWT in URL; no secret exposed to frontend /
NEXT_PUBLIC_*. - New sensitive fields added to Pino redaction config.
- File uploads pass all 4 security checks.
Evidence — Cite the file/line and the specific rule; show the unredacted field or unbounded schema.
Verdict — Shared verdict envelope. FAIL on any leak/injection/validation
gap. NEVER overrides CLAUDE.md / rules/00-master-rules.md.
Related — authentication-reviewer, authorization-idor-reviewer, api-contract-reviewer.
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.
- 5d ago First seen · 53 lines · 0 tokens per session scan A ef84ce98a967
security-reviewer is an agent published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed 2d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 623 tokens. 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 agents, from other repositories
SPEC_RECONSTRUCTION_FIDELITY
RefinementAgent.run() (via diffformat.difforfull) and DesignAgent.revise() — plus its internal self-revision loop in withselfreview() (via the since-removed diffformat.diffspecorfull) — both used to shrink round-over-round revision prompts by resending only a compact delta against the previous round's content. Both…
docs-writer
Expert technical documentation specialist for creating comprehensive, user-friendly documentation across all project types. Use proactively for API docs, user guides, and technical documentation.
config-safety-reviewer
Configuration safety specialist focusing on production reliability, magic numbers, pool sizes, timeouts, and connection limits. Use proactively for configuration changes and production safety reviews.
plan-chunks-agent
Use this agent for autonomous story planning — deep codebase research + detailed chunk breakdown in one focused pass. Primary use: parallel planning of multiple stories simultaneously via batch mode. Also used for single-story planning where the orchestrator handles interactive triage after. The orchestrator MUST…
alchemist
Creative technologist who sees the browser as an unexplored physics engine. Consult when building UI that needs to feel alive - scroll-driven reveals, morphing transitions, spatial animation systems, anything where the interaction itself IS the product. Thinks in weight, tension, and breath before thinking in code.…
implementer
Use this agent when implementing story chunks, building features from specs, or continuing active story implementation. Owns the implement → validate → refine loop for each chunk. Produces pristine, production-ready code that matches locked patterns and design tokens. Context: Orchestrator is implementing a story and…