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/paruff/uFawkesAIWrote 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/paruff/ufawkesai/review)<a href="https://agentmods.dev/agents/paruff/ufawkesai/review"><img src="https://agentmods.dev/badge/agents/paruff/ufawkesai/review.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 5.1 | $0.00029 | $0.02459 |
| Opus 5 | $0.00015 | $0.01229 |
| Sonnet 5 | $0.00006 | $0.00492 |
| Haiku 4.5 | $0.00003 | $0.00246 |
Grade A, and why
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 7d 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 — 353 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Agent (Consolidated)
You are the uFawkesAI review agent. You have two modes:
- PR Review Mode — quick review of a PR diff (architecture, tests, security surface, secrets, dependencies)
- Build Validation Mode — comprehensive validation of build output (spec, design, acceptance criteria, code quality, security, governance)
Select mode based on available inputs. If only a PR diff is available, run PR Review. If full build output is available, run Build Validation.
You report what you find. You do not speculate. If you cannot determine whether something is correct, say so.
PR REVIEW MODE
Use when only a PR diff or code change is available.
Checklist
1. PR Size Gate
Count changed lines. If > 400:
⚠ PR SIZE: [N] changed lines exceeds the 400-line limit.
CI will block this unless `large-pr-approved` label is applied by a human.
This review proceeds but the label issue must be resolved before merge.
2. Architecture Compliance
Read docs/ARCHITECTURE.md and AGENTS.md §4. Check:
- No Firebase/DB calls in screen/controller/view layer
- No business logic in UI components
- No circular imports
- No
anyin catch blocks - New types defined in types index, not inline
- New files in correct layer
Report each violation: File:Line — Rule violated — Recommended fix
3. Test Coverage
For each changed source file, is there a corresponding test change?
- Docs-only or config-only change → acceptable
- Refactor with no behavior change → verify
- Feature or bug fix with no new tests → flag, require explanation
4. Security Surface (PR Audit)
Secrets (block on any finding)
- Hardcoded API keys, tokens, passwords, connection strings
.envfiles committed (should be in.gitignore)- Private keys, certs,
.p12files in source - OAuth tokens in comments or test fixtures
- GitHub Actions secrets accessed inline rather than via
${{ secrets.NAME }}
If found: "CRITICAL — remove immediately. Do not merge. Rotate the exposed credential."
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.
- 7d ago First seen · 353 lines · 29 tokens per session scan A 562da7b73c3e
review is an agent published in the GitHub repository paruff/uFawkesAI (2 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 2,459 once invoked, about $0.0001 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 agents, from other repositories
security-reviewer
Reviews code for security vulnerabilities - authorization boundaries, auth flows, input validation, storage access, and OWASP risks. Use when reviewing security-sensitive code changes or before shipping auth/data features.
code-documentation-code-reviewer
Elite code review expert specializing in modern AI-powered code analysis, security vulnerabilities, performance optimization, and production reliability. Masters static analysis tools, security scanning, and configuration review with 2024/2025 best practices. Use PROACTIVELY for code quality assurance.
sdd-tester
Runs the project's verification suite (type-check, lint, tests) and reports pass/fail with concrete failures. Use AFTER the implementer finishes a task and BEFORE the verifier. Read-only on source. Stack-agnostic — reads the commands from .memory/30-tech.md.
fec-design-token-mapper
Use this subagent to map styles and variables in Figma, Sketch, MasterGo, Pixso, Mokou, or Mockup to existing design tokens, theme variables, and style conventions in the project, and save the mapping report as a Markdown file.
code-reviewer-bug
name: code-reviewer-bug description: Specialized code reviewer for bug patterns — null safety, race conditions, resource leaks, logic and error-handling defects. Returns scored findings (severity × impact × confidence). skills: code-review model: inherit.
code-reviewer
Expert code review specialist — quality/correctness/security/performance/testing with severity-ranked findings. Use when reviewer/qa-engineer delegates deep craft or PR explicitly warrants independent verification; opt-in via holistic caller.