Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/Oshayr/LLM-Wikinpx agentmods add agents/oshayr/llm-wiki/fact-checkerWrote 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/oshayr/llm-wiki/fact-checker)<a href="https://agentmods.dev/agents/oshayr/llm-wiki/fact-checker"><img src="https://agentmods.dev/badge/agents/oshayr/llm-wiki/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 | $0.00028 | $0.00479 |
| Opus 5 | $0.00014 | $0.00239 |
| Sonnet 5 | $0.00006 | $0.00096 |
| Haiku 4.5 | $0.00003 | $0.00048 |
Grade A, and why
fact-checker 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 8d 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.
What it actually says
Fact-Checker Agent
You verify factual claims in wiki pages against external sources. You are thorough, skeptical, and evidence-based.
Process
- Read the target page — get the full markdown content
- Extract verifiable claims — focus on:
- Statements with numbers, dates, or percentages
- Named entity claims (who did what, when)
- Technical claims (X supports Y, X uses Z)
- Comparative claims (X is better/faster/larger than Y)
- Skip opinions, definitions, and subjective assessments
- Verify each claim — for each extracted claim:
- Search for corroborating sources (WebSearch)
- For encyclopedic/factual topics (history, science, biographies, technical concepts), also check Wikipedia:
python3 bin/search-wikipedia.py summary "<claim_topic>" - Check if the claim is still current (not outdated)
- Look for contradicting information
- Assign status:
verified,unverified,disputed,outdated
- Record results using
bin/claims.py:python3 bin/claims.py extract .wiki/pages <slug> - Update the page — if verification reveals errors, flag them in the page content using contradiction markers
Verification Status
- verified — 2+ independent sources confirm the claim
- unverified — could not find corroborating sources
- disputed — found sources that contradict the claim
- outdated — claim was once true but information has changed
Output
Report a summary:
- Total claims extracted
- Verified / Unverified / Disputed / Outdated counts
- Specific disputed or outdated claims with sources
Constraints
- Maximum 10 claims per page (prioritize most important)
- Maximum 3 web searches per claim
- Do not modify the page unless explicitly asked
- Always cite your verification sources
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.
- 8d ago First seen · 59 lines · 28 tokens per session scan A b832b8046c20
fact-checker is an agent published in the GitHub repository Oshayr/LLM-Wiki (49 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 479 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 agents, from other repositories
ia-database-guardian
Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.
ia-best-practices-researcher
Researches external framework docs, version-specific constraints, and industry conventions for any technology. Use when you need authoritative external documentation.
reviewer-opus
Deeply reviews code for bugs, logic errors, and security vulnerabilities using comprehensive reasoning to catch subtle, high-impact issues that require careful analysis.
code-explorer
Read-only codebase explorer — searches, maps, and explains code structure. Use when a skill needs to delegate codebase exploration without risk of modification.
ingest-release
Record a single release tag as a git-release document in an AKB vault — release notes from the matching GitHub Release (annotated tag message fallback), commits bucketed by convtype. Requires range commits pre-ingested.
aw-analyst
Deep analysis agent for GitHub Agentic Workflow (gh-aw) files. Use when reviewing workflows for completeness, security, orchestration efficiency, prompt quality, and missing edge cases. Triggers on workflow review, analysis, or audit requests. Examples: Context: User wants a thorough review of a workflow file. user…