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 commands/nicobailon/visual-explainer/fact-checkgit clone --depth 1 https://github.com/nicobailon/visual-explainerWhat 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 | $0.00013 | $0.00225 |
| Opus 5 | $0.00006 | $0.00112 |
| Sonnet 5 | $0.00003 | $0.00045 |
| Haiku 4.5 | $0.00001 | $0.00022 |
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 2d 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
Load the visual-explainer skill and fact-check the document named by $@. If no argument is given, use the most recently modified HTML file in ~/.agent/diagrams/.
Claim extraction
Read the target document. Extract verifiable claims about file paths, function/type/module names, behavior, architecture, data flow, APIs, commands, dependencies, tests, performance/security assertions, and git history. Skip subjective design opinions.
Verification
For each claim, inspect the actual source or git history. Re-read referenced files. For diff reviews, compare before/after with git show or the relevant range. For plan docs, verify referenced files/functions/types exist and behave as described.
Classify claims as verified, corrected, unsupported, or unverifiable. Preserve the document’s structure. Correct factual errors in place and add a verification summary that lists what was checked and changed. For HTML, match the existing page style and open it in the browser. For markdown, report the path in chat.
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.
- 2d ago First seen · 17 lines · 13 tokens per session scan A cce9ebbc12ca
fact-check is a command published in the GitHub repository nicobailon/visual-explainer (9,621 stars, last pushed 4d ago), licensed MIT. It adds 13 tokens to every session and 225 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 commands, from other repositories
git
Git operations with intelligent commit messages and workflow optimization.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.