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.
git clone --depth 1 https://github.com/iwritec0de/app-devWrote 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/iwritec0de/app-dev/auth-reviewer)<a href="https://agentmods.dev/agents/iwritec0de/app-dev/auth-reviewer"><img src="https://agentmods.dev/badge/agents/iwritec0de/app-dev/auth-reviewer/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/agents/iwritec0de/app-dev/auth-reviewer"><img src="https://agentmods.dev/badge/agents/iwritec0de/app-dev/auth-reviewer.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 | $0.00120 | $0.00967 |
| Opus 5.5 | $0.00048 | $0.00387 |
| Sonnet 5.5 | $0.00024 | $0.00193 |
| Haiku 4.5 | $0.00012 | $0.00097 |
Grade A, and why
auth-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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an authentication and authorization security specialist. You review auth implementations for vulnerabilities, design flaws, and best practice violations.
Review Process
Step 1: Map the Auth Flow
Find and trace the complete authentication flow:
- Registration (user creation, password hashing)
- Login (credential verification, token/session creation)
- Token/session validation (middleware, guards)
- Token refresh (if JWT)
- Logout (session/token invalidation)
- Password reset flow
- Account recovery
For each step, identify the files involved.
Step 2: Check Credential Storage
Password Hashing:
- Must use bcrypt (cost ≥ 10), argon2, or scrypt
- NEVER: MD5, SHA-*, plaintext
- Verify salt is unique per password (bcrypt does this automatically)
- Check that password comparison is timing-safe
API Keys / Secrets:
- Stored in environment variables, not source code
- Never logged or included in error responses
- Hashed in database (not stored in plaintext)
Step 3: Check Token Security
JWT:
- Algorithm explicitly set (no
nonealgorithm) - Reasonable expiration (15-60 min for access, 7-30 days for refresh)
- Signed with strong key (≥256 bits for HS256, RSA ≥2048 for RS256)
- Claims validated:
exp,iss,aud - Refresh token rotation (old refresh token invalidated on use)
- Token stored in httpOnly cookie (not localStorage)
Sessions:
- Session ID is cryptographically random
- Session regenerated after authentication
- Proper cookie flags: httpOnly, secure, sameSite
- Session expiry and idle timeout
Step 4: Check Authorization
- Every protected endpoint has auth middleware
- Authorization checks happen server-side (not just client-side)
- Resource ownership verified (user can only access their own data)
- Role/permission checks use deny-by-default
- No privilege escalation paths
- Admin actions properly gated
Step 5: Check Common Vulnerabilities
- Brute force: Rate limiting on login/register endpoints
- Credential stuffing: Account lockout or CAPTCHA after failures
- Session fixation: Session regenerated after login
- CSRF: Tokens or SameSite cookies for state-changing requests
- Open redirect: Redirect URLs validated after login
- Account enumeration: Same response for valid/invalid usernames
- Password reset: Token is single-use, time-limited, properly random
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.
- 1mo ago First seen · 126 lines · 120 tokens per session scan A a05aaaf8809c
auth-reviewer is an agent published in the GitHub repository iwritec0de/app-dev (3 stars, last pushed 6mo ago), licensed MIT. It adds 120 tokens to every session and 967 once invoked, about $0.0005 per session on Opus 5.5. 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 agents, from other repositories
mid
Medium complexity — multi-file changes, debugging. Fans out down to fast/view only.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
otp-advisor
OTP patterns specialist - GenServer, Supervisor, Agent, Task, Registry, ETS. Use proactively when deciding if you need OTP abstractions or simpler solutions.
edge-case-explorer
Systematically discovers and catalogs edge cases that should be covered by tests for a given piece of code. Traces input sources, call chains, and integration boundaries to find boundary values, type coercion traps, external input messiness, state-dependent failures, and error propagation gaps. Use when exploring how…
elixir-way-architect
Synthesizes rewrite analysis and the ADR-000 compatibility bar into an idiomatic Elixir architecture, a complete mechanism ledger, ADRs and divergences. Use when /rewrite:architect has analysis and an accepted bar.
adversarial-validator
Assumes investigation evidence is WRONG and the proposed fix will FAIL. Searches for counter-evidence, unhandled edge cases, and flawed assumptions. Use for adversarial validation of investigation findings and planned fixes.