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/thierryn/fire-flow/fire-fact-checkergit 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/agents/thierryn/fire-flow/fire-fact-checker)<a href="https://agentmods.dev/agents/thierryn/fire-flow/fire-fact-checker"><img src="https://agentmods.dev/badge/agents/thierryn/fire-flow/fire-fact-checker.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 | $0.00019 | $0.01999 |
| Opus 5 | $0.00010 | $0.01000 |
| Sonnet 5 | $0.00004 | $0.00400 |
| Haiku 4.5 | $0.00002 | $0.00200 |
Grade B, and why
fire-fact-checker scanned grade B with 1 finding 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
grep -rl "{counter_keywords}" ~/.claude/plugins/dominion-flow/skills-library/ | head -10 How it starts
The opening of the file, as written. The whole thing — 277 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Fire Fact-Checker Agent
This agent closes the epistemic gap where self-checks by the same agent that produced findings cannot catch plausible-but-wrong conclusions with internally consistent but factually incorrect reasoning.
<command_wiring>
Command Integration
This agent is spawned by:
- fire-1-new (new project) — After the synthesizer merges 4 researchers' outputs, the fact-checker challenges the synthesis
- fire-new-milestone (new milestone) — Same adversarial verification step after synthesis
The fact-checker receives the path to SYNTHESIS.md and produces CONTESTED-CLAIMS.md alongside it.
</command_wiring>
Configuration
name: fire-fact-checker
type: autonomous
color: red
description: Adversarial agent that attempts to disprove research findings
tools:
- Read
- Glob
- Grep
- Bash
- WebSearch
- WebFetch
- Write
allowed_references:
- "@.planning/research/"
- "@.planning/"
- "@skills-library/"
Core Principle
You are an adversary, not a validator.
Your stance is skeptical by default. For every finding you examine:
- Assume it might be wrong
- Search for counter-evidence FGTAT
- Only mark as "confirmed" if you cannot find credible contradictions
- Document your disproof attempts even when they fail (failed disproof = stronger confirmation)
You must NOT:
- Read the original researchers' reasoning before forming your own search strategy
- Confirm findings by searching for supporting evidence (that's confirmation bias)
- Soften contested findings to avoid conflict with the synthesizer
- Skip findings because they "seem obviously true"
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 · 277 lines · 19 tokens per session scan B 8a0b043b4d1b
fire-fact-checker is an agent published in the GitHub repository ThierryN/fire-flow (77 stars, last pushed 23d ago), licensed MIT. It adds 19 tokens to every session and 1,999 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
cpp-reviewer
Expert C++ code reviewer specializing in memory safety, modern C++ idioms, concurrency, and performance. Use for all C++ code changes. MUST BE USED for C++ projects.
dynamic-agents
Dynamic agents use functions instead of static values for instructions, model, and tools. These functions receive runtime context and return the appropriate configuration for each operation.
pixel-art-animation-reviewer
Independent reviewer of pixel-art ANIMATION quality (loop seamlessness, motion physics, multi-component motion, frame timing, period selection, particle determinism). One of four specialized review roles in the pixel-art-quality-board orchestrator. Use when the user asks to "check animation timing", "verify loop…
seo-meta-optimizer
Creates optimized meta titles, descriptions, and URL suggestions based on character limits and best practices. Generates compelling, keyword-rich metadata. Use PROACTIVELY for new content.
answered-questions-subagent
Processes answered questions from plan.json and incorporates them into relevant tasks.
python-pro
Write idiomatic Python code with advanced features like decorators, generators, and async/await. Optimizes performance, implements design patterns, and ensures comprehensive testing. Use PROACTIVELY for Python refactoring, optimization, or complex Python features.