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/bengous/claude-code-pluginsWrote 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/bengous/claude-code-plugins/fact-check)<a href="https://agentmods.dev/commands/bengous/claude-code-plugins/fact-check"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/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/commands/bengous/claude-code-plugins/fact-check"><img src="https://agentmods.dev/badge/commands/bengous/claude-code-plugins/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 | $0.00010 | $0.00422 |
| Opus 5.5 | $0.00004 | $0.00169 |
| Sonnet 5.5 | $0.00002 | $0.00084 |
| Haiku 4.5 | $0.00001 | $0.00042 |
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 1mo 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
Verify the following claim using web search:
Process
- Search broadly - Run multiple searches with different phrasings to find diverse sources
- Evaluate sources - Prioritize academic papers, official sources, and established journalism over blogs or social media
- Cross-reference - Look for independent confirmation across at least 2-3 sources
- Report - Present findings with clear sourcing
<parallel_search_guidance> When investigating a claim, run multiple WebSearch queries in parallel with different angles (e.g., the claim itself, key terms, potential counterarguments). This builds a more complete picture efficiently. </parallel_search_guidance>
Output Format
Verdict
<verdict_definitions>
- Supported: Multiple reliable sources confirm the claim
- Partially Supported: Core claim is accurate but contains inaccuracies or missing nuance
- Disputed: Credible sources disagree; no clear consensus exists
- Unsupported: No reliable sources confirm the claim, or evidence contradicts it
- Unverifiable: Insufficient information available to assess the claim </verdict_definitions>
Evidence
Summarize the key findings from sources
Sources
List the sources consulted as markdown links
Guidelines
- State your interpretation if the claim is ambiguous before searching
- Note disagreements between sources and explain why you weighted certain sources higher
- Separate factual claims from opinions or predictions
- Ask for clarification only if the claim is too vague to search meaningfully
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.
- 1mo ago Changed · +1 lines 1835554d5d53
- 1mo ago Changed a554e1b6beaf
- 1mo ago First seen · 57 lines · 10 tokens per session scan A 9be6e5e92930
fact-check is a command published in the GitHub repository bengous/claude-code-plugins (6 stars, last pushed today), licensed MIT. It adds 10 tokens to every session and 422 once invoked, about $0.0000 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 2026-09-03.
Other commands, from other repositories
spec-research
A requirements-research command that turns a request into a set of constraints and checkable success criteria. It explores the relevant parts of a project in parallel and creates a structured proposal.
triage
Triage Linear issue with comprehensive analysis.
land
Resolve and squash merge one named, currently authorized pull request.
sync
Manually trigger plan-sync to update downstream task specs after implementation drift.
slack-gif-creator
Toolkit for creating animated GIFs optimized for Slack, with validators for size constraints and composable animation primitives. This skill applies when users request animated GIFs or emoji animations for Slack from descriptions like "make me a GIF for Slack of X doing Y".
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.