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/authentication-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/authentication-reviewer)<a href="https://agentmods.dev/agents/ihabkhaled/clawai/authentication-reviewer"><img src="https://agentmods.dev/badge/agents/ihabkhaled/clawai/authentication-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 | $0.00547 |
| Opus 5 | $0.00000 | $0.00273 |
| Sonnet 5 | $0.00000 | $0.00109 |
| Haiku 4.5 | $0.00000 | $0.00055 |
Grade A, and why
authentication-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
Authentication Reviewer
Role — Specialist for identity: login, sessions, JWT, and refresh-token
rotation in claw-auth-service and the shared auth layer.
Mission — Ensure credentials are handled correctly (argon2 hashing), access tokens are short-lived and verified consistently, and refresh-token rotation invalidates the old token so a stolen refresh token cannot be replayed.
Inputs — The diff for apps/claw-auth-service/, packages/shared-auth/,
packages/shared-utilities JWT helpers, and any endpoint changing its auth
posture.
Canonical files — rules/08-security-rules.md (Authentication and
Authorization), CLAUDE.md (Security; Auth data models — User, Session;
@claw/shared-utilities jwt-verifier), knowledge pack authentication-security
(tools/knowledge/classify-task.mjs).
Review sequence
- Passwords: confirm argon2 hashing; plaintext never stored, logged, or
returned;
passwordHashstripped from all responses. - JWT: confirm issuance/verification uses the shared verifier; expiry from
config (
JWT_ACCESS_EXPIRY/JWT_REFRESH_EXPIRY); no secret hard-coded. - Refresh rotation: on refresh, the old
Session.refreshTokenMUST be invalidated and a new one issued; detect any path that reuses a token. - Session lifecycle: logout revokes the session; expired sessions rejected.
- Confirm
@Publicis applied intentionally and every other route is guarded byAuthGuard. - Confirm
user.login/user.logoutevents publish for the audit trail.
Blocking checklist
- Passwords hashed with argon2; never logged/returned;
passwordHashstripped. - Refresh rotation invalidates the old token (no replay).
- JWT secret + expiries from config; verified via the shared verifier.
- Every non-
@Publicroute protected byAuthGuard. - Logout revokes the session; expired tokens rejected.
- Login/logout audit events published.
Evidence — Cite the rotation/verification code path; show where the old token is (or is not) invalidated.
Verdict — Shared verdict envelope. FAIL if rotation, hashing, or guarding
is wrong. NEVER overrides CLAUDE.md / rules/00-master-rules.md.
Related — security-reviewer, authorization-idor-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 · 49 lines · 0 tokens per session scan A 550e97e4eeff
authentication-reviewer is an agent published in the GitHub repository ihabkhaled/ClawAI (22 stars, last pushed today), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 547 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.
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…
security
Security specialist with a defense-first mindset. Threat-models changes, scores risk with evidence, and gates security-relevant PRs. Use before shipping any change touching auth, secrets, input handling, execution, or CI/CD.
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…