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/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-vuln-scan)<a href="https://agentmods.dev/commands/thierryn/fire-flow/fire-vuln-scan"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-vuln-scan/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/commands/thierryn/fire-flow/fire-vuln-scan"><img src="https://agentmods.dev/badge/commands/thierryn/fire-flow/fire-vuln-scan.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 | $0.00018 | $0.04119 |
| Opus 5 | $0.00009 | $0.02060 |
| Sonnet 5 | $0.00004 | $0.00824 |
| Haiku 4.5 | $0.00002 | $0.00412 |
Grade A, and why
fire-vuln-scan scanned grade A with 2 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Pattern: fetch(req.body.url) or axios.get(req.query.callback) Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- [ ] Command injection: User input in child_process.exec/spawn/execFile How it starts
The opening of the file, as written. The whole thing — 493 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/fire-vuln-scan
AI-powered application vulnerability scanner — find what regex-based tools miss
Purpose
Scan application codebases for OWASP Top 10 vulnerabilities using Claude's code reasoning — not pattern matching. Inspired by Anthropic's Claude Code Security (launched 2026-02-20), which found 500+ bugs that humans missed for decades.
What this is: Application security scanner (finds SQL injection, XSS, broken auth in YOUR code)
What this is NOT: Agent security scanner (that's /fire-security-scan — protects Claude from prompt injection)
Arguments
arguments:
target_path:
required: false
type: string
description: "Directory or file to scan. Defaults to current project root."
example: "/fire-vuln-scan c:\\path\\repos\\MY-PROJECT"
optional_flags:
--deep: "AI-powered reasoning trace per finding (slower, fewer false positives)"
--category: "Focus on one category: injection | auth | data | config | mern | all (default: all)"
--fix-preview: "Show suggested fix code for each finding"
--report: "Save full report to .planning/security/ AND Claude Reports folder"
--server-only: "Scan only server-side code (skip client/frontend)"
--client-only: "Scan only client-side code (skip server/backend)"
--critical-only: "Only report CRITICAL and HIGH severity findings"
Process
Step 1: Enumerate Target Files
+------------------------------------------------------------------------------+
| POWER VULN SCAN |
+------------------------------------------------------------------------------+
| |
| Target: {path} |
| Mode: {quick | deep} |
| Category: {all | injection | auth | data | config | mern} |
| Agents: {3-4 parallel scanners} |
| |
+------------------------------------------------------------------------------+
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 · 493 lines · 18 tokens per session scan A 07fb76d73416
fire-vuln-scan is a command published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 28d ago), licensed MIT. It adds 18 tokens to every session and 4,119 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 2 findings (makes network calls, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
cpp-build
Fix C++ build errors, CMake issues, and linker problems incrementally. Invokes the cpp-build-resolver agent for minimal, surgical fixes.
flutter-build
Fix Dart analyzer errors and Flutter build failures incrementally. Invokes the dart-build-resolver agent for minimal, surgical fixes.
dev
Developer tools — debug, commit, PR, code review, refactoring.
triage
Triage a failing test, panic, CI failure, or error log.
code-quality
Code review and bug prediction — find quality issues, style violations, and likely bugs.
fix-test
Auto-diagnose and fix failing tests — identifies root causes and applies fixes.