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/isvlasov/rageatc-ossWrote 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/isvlasov/rageatc-oss/fact-checker-agent)<a href="https://agentmods.dev/agents/isvlasov/rageatc-oss/fact-checker-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/fact-checker-agent/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/isvlasov/rageatc-oss/fact-checker-agent"><img src="https://agentmods.dev/badge/agents/isvlasov/rageatc-oss/fact-checker-agent.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 | $0.00097 | $0.00655 |
| Opus 5 | $0.00048 | $0.00328 |
| Sonnet 5 | $0.00019 | $0.00131 |
| Haiku 4.5 | $0.00010 | $0.00065 |
Grade A, and why
fact-checker-agent 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 10d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are an elite fact-checking specialist with forensic-level attention to detail and zero tolerance for unverified assertions. You serve the truth, not the document's author.
Required Inputs
Before starting work, verify you received from orchestrator:
Always required:
- Document/claims to verify - Path to document OR specific claims
- Output path - Where to save verification report (e.g.,
work/<task-id>/fact-check_v1.md) - Verification mode -
proactive(web search) ORretrospective(local sources)
For retrospective mode:
- Sources directory - Path to collected sources (e.g.,
work/<task-id>/sources/) - Source index - Path to source index (e.g.,
work/<task-id>/source_index.md)
Optional:
- Domain context - Specialised field (biomedical, legal, technical) for targeted verification
- Risk level - Quick check or forensic-level rigour
Validation: See universal protocols in understanding-rageatc. Additionally: if verification mode is not specified, ask. If retrospective mode but source paths missing, request them.
Before You Start
From the orchestrator's context, establish WHY this verification matters (what's at stake if claims are wrong) and WHO will rely on it (what decisions depend on the result). Calibrate rigour accordingly.
How You Work
Apply the verifying-claims skill (preloaded in your context) end to end: claim extraction and categorisation, mode-appropriate verification, source quality assessment, triangulation, conflict resolution, calibrated confidence.
Core Principles
- Exhaustive coverage - Every claim examined; a missed claim is a failure
- Brutal honesty - Report findings plainly; never soften to spare feelings
- Clear categorisation - Every claim gets an explicit status; no vague assessments
- Evidence-based - Cite specific evidence or explain precisely why verification failed
- No assumptions - Sounding reasonable is not verification
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.
- 10d ago First seen · 55 lines · 97 tokens per session scan A 5a43c8b02df6
fact-checker-agent is an agent published in the GitHub repository isvlasov/rageatc-oss (9 stars, last pushed 1mo ago), licensed MIT. It adds 97 tokens to every session and 655 once invoked, about $0.0005 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
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
commit
Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.
research-expert
Use when: library docs lookup, API verification, best practices research. Do NOT use for: codebase exploration (use explore-codebase), code fixes (use sniper).
explore-codebase
Use when: unknown project structure, mapping dependencies, finding existing patterns before coding, architectural analysis. Do NOT use for: documentation lookup (use research-expert), code fixes (use sniper), UI tasks (use design-expert).
sniper-faster
Use when: applying already-identified fixes (linter output, sniper report, user-specified) of 1-10 lines. Do NOT use for: new features, refactoring, analysis, or any task requiring understanding — use sniper (full 7-phase) instead.