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 commands/thierryn/fire-flow/fire-7-reviewgit clone --depth 1 https://github.com/ThierryN/fire-flowWrote 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/commands/thierryn/fire-flow/fire-7-review)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-7-review"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-7-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 | $0.00011 | $0.02695 |
| Opus 5 | $0.00005 | $0.01347 |
| Sonnet 5 | $0.00002 | $0.00539 |
| Haiku 4.5 | $0.00001 | $0.00269 |
Grade A, and why
fire-7-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 6d 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 — 410 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-7-review
Comprehensive code review through multiple expert lenses
Purpose
Perform deep code review using 16 specialized reviewer personas (14 original + Simplicity Guardian + Qt Thread Guardian), each examining the code from their unique perspective. Inspired by compounding-engineering's multi-perspective approach, this catches issues that single-reviewer passes miss. In v8.0, also available in automatic mode via the fire-reviewer agent.
Arguments
arguments:
target:
required: true
type: string
description: "What to review - can be a file, directory, PR number, or 'phase N'"
examples:
- "/fire-7-review src/auth/"
- "/fire-7-review PR#123"
- "/fire-7-review phase 2"
optional_flags:
--perspectives: "Comma-separated list of specific personas to use (default: all)"
--depth: "shallow | normal | deep (default: normal)"
--focus: "Security focus area: auth, data, api, all (default: all)"
--parallel: "Run persona reviews in parallel (default: true)"
--output: "Report output path (default: .planning/reviews/)"
The 14 Reviewer Personas
Security Reviewers (4)
| Persona | Focus | Catches |
|---|---|---|
| Security Hawk | OWASP Top 10, injection, auth flaws | Critical vulnerabilities |
| Data Guardian | PII exposure, encryption, privacy | Data leaks, compliance |
| API Sentinel | Auth tokens, rate limits, CORS | API abuse vectors |
| Crypto Auditor | Encryption strength, key handling | Weak crypto, key exposure |
Quality Reviewers (5)
| Persona | Focus | Catches |
|---|---|---|
| Simplicity Guardian | Over-engineering, unnecessary abstraction, premature optimization | Code that's complex when it could be simple |
| Performance Eagle | N+1 queries, memory, bottlenecks | Performance issues |
| Test Skeptic | Coverage gaps, test quality | Untested edge cases |
| Error Hunter | Error handling, edge cases | Unhandled failures |
| Type Guardian | Type safety, any usage | Runtime type errors |
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.
- 6d ago First seen · 410 lines · 11 tokens per session scan A 023ec5d3d040
fire-7-review is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 24d ago), licensed MIT. It adds 11 tokens to every session and 2,695 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 2026-08-30.
Other commands, from other repositories
cpp-review
Comprehensive C++ code review for memory safety, modern C++ idioms, concurrency, and security. Invokes the cpp-reviewer agent.
flutter-review
Review Flutter/Dart code for idiomatic patterns, widget best practices, state management, performance, accessibility, and security. Invokes the flutter-reviewer agent.
refactor-clean
Remove dead code and consolidate duplicates.
code-review
Review code for quality, security, and maintainability.
fastapi-review
Review a FastAPI application for architecture, async correctness, dependency injection, Pydantic schemas, security, performance, and testability.
go-review
Go code review for idiomatic patterns.