Borrowing it
Nothing to install: this file belongs to collaborative-deep-research/agent-papers-cli. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/collaborative-deep-research/agent-papers-cli/main/.claude/skills/fact-check/SKILL.mdgit clone --depth 1 https://github.com/collaborative-deep-research/agent-papers-cliWrote 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/skills/collaborative-deep-research/agent-papers-cli/fact-check)<a href="https://agentmods.dev/skills/collaborative-deep-research/agent-papers-cli/fact-check"><img src="https://agentmods.dev/badge/skills/collaborative-deep-research/agent-papers-cli/fact-check/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/skills/collaborative-deep-research/agent-papers-cli/fact-check"><img src="https://agentmods.dev/badge/skills/collaborative-deep-research/agent-papers-cli/fact-check.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 | $0.00033 | $0.00385 |
| Opus 5.5 | $0.00013 | $0.00154 |
| Sonnet 5.5 | $0.00007 | $0.00077 |
| Haiku 4.5 | $0.00003 | $0.00038 |
Grade A, and why
fact-check scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
Fact-check the following claim: "$ARGUMENTS"
1. Decompose
Break the claim into specific, verifiable sub-claims. List them explicitly before searching.
2. Search for Evidence
For each sub-claim:
paper-search google web "<sub-claim as question>"
paper-search semanticscholar snippets "<sub-claim keywords>"
paper-search semanticscholar papers "<sub-claim keywords>" --limit 5
3. Verify Sources
For each promising source:
paper read <arxiv_id> <relevant section> # for academic papers
paper-search browse <url> # for web pages
Prefer primary sources (original papers, official data) over secondary reports.
4. Assess
For each sub-claim, assign a verdict:
- Supported: strong evidence from multiple reliable sources
- Partially supported: some evidence, with caveats
- Unsupported: no evidence found, or evidence contradicts the claim
- Uncertain: insufficient evidence to judge
5. Report
Present:
- The original claim
- Each sub-claim with its verdict and supporting evidence
- An overall assessment
- All sources cited with URLs
Guidelines
- Always cite specific sources — never state a verdict without evidence.
- Distinguish between "no evidence found" and "evidence contradicts."
- Note the quality and recency of sources.
- If a claim is about a specific paper, read that paper directly rather than relying on summaries.
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.
- 2mo ago First seen · 55 lines · 33 tokens per session scan A 13747a2106a1
fact-check is a skill published in the GitHub repository collaborative-deep-research/agent-papers-cli (50 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 33 tokens to every session and 385 once invoked, about $0.0001 per session on Opus 5.5. 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.
fact-check compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| fact-checkcollaborative-deep-research/agent-papers-cli | Skill | 50 | 7mo ago | Apache-2.0 | A | 33 | Claude Code |
| imagegenopenai/codex | Skill | 133k | yesterday | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 99k | yesterday | Apache-2.0 | A | 19 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 313k | 3d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 95 | Claude Code |
| next-partial-prefetching-adoptionvercel/next.js | Skill | 143k | yesterday | MIT | A | 103 | Claude Code |