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/theclaymethod/artifactureWrote 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/theclaymethod/artifacture/fact-check)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/fact-check"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/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/theclaymethod/artifacture/fact-check"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/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 | $0.00011 | $0.00522 |
| Opus 5.5 | $0.00004 | $0.00209 |
| Sonnet 5.5 | $0.00002 | $0.00104 |
| Haiku 4.5 | $0.00001 | $0.00052 |
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.
This is a copy
88% identical to fact-check — 67 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 35 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load SKILL.md, then fact-check: $@
Find the target and source
Use $1 when supplied. Otherwise use the most recently modified HTML file in ~/.agent/diagrams/ (ls -t ~/.agent/diagrams/*.html | head -1). No creative clarification is needed.
For generated HTML, locate its sibling or referenced MDX/TSX source. Inspect the rendered artifact, correct the source, and re-export with npm run ve:export. Edit HTML directly only for legacy output or when no source can be found; record that limitation. Edit Markdown and other text documents in place.
Identify the document's comparison point: the git ref for a diff review, the plan for a plan review, or the stated history window for a recap. Do not compare every document against an unstated current baseline.
Check each claim
Extract and verify:
- Numbers: file, line, function, module, and test counts.
- Names: paths, symbols, types, and signatures.
- Behavior: conditions, effects, and before/after descriptions.
- Structure: imports, dependencies, and module boundaries.
- History: dates, commits, and attributions.
Read every referenced file. Rerun relevant git commands. For a diff, inspect both git show <ref>:file and the working tree so before and after cannot be swapped. For plans, verify that referenced files and symbols exist and behave as described. For recaps, verify the activity narrative against the stated window.
Classify each claim as confirmed, corrected, or unverifiable. Cite the evidence for corrections. A claim that needs unavailable runtime evidence remains unverifiable. Leave opinions and design judgments alone.
Correct and report
Fix inaccurate quantities, names, paths, behavior, and reversed comparisons. Rewrite a whole section only when its premise is wrong. Preserve the surrounding organization, formatting, and styling. Change diagram labels or edges only when they contain a factual error.
Add a verification summary with the total checked, confirmed count, corrections and their sources, and unverifiable claims. For Markdown, append ## Verification Summary. For HTML, use a plain section that matches the page; read references/css-patterns.md only if needed to preserve its styling.
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 · -31 lines · -6 tokens per session 8c2426f9f99b
- 1mo ago First seen · 66 lines · 17 tokens per session scan A c9458faa4128
fact-check is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 11 tokens to every session and 522 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 88% identical to fact-check, differing in 67 lines, and is treated as a copy.
Other commands, from other repositories
init
Install the formatters this repository needs, with every command visible before it runs.
simplify
The over-engineering review: five tags (delete, stdlib, native, yagni, shrink), a mandatory replacement per finding, and a real null result when there is nothing to cut.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
extend
Capture a mid-PR sub-idea and implement it onto the current open PR's branch — no new branch, no new PR. Preserves Verify → Review → Deliver.
fec-smell
Diagnose frontend code smells with evidence and candidate refactorings without changing business code.
security-review
Depth-first security audit of the current git diff — OWASP Top 10, secret leakage, insecure-by-default APIs, and language-specific foot-guns. Pass a PR number to audit a specific PR's diff.