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/diff-review)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/diff-review"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/diff-review/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/diff-review"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/diff-review.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 | $0.00012 | $0.00475 |
| Opus 5.5 | $0.00005 | $0.00190 |
| Sonnet 5.5 | $0.00002 | $0.00095 |
| Haiku 4.5 | $0.00001 | $0.00047 |
Grade A, and why
diff-review 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.
How it starts
The opening of the file, as written. The whole thing — 40 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Load SKILL.md. Use this command for reviewer findings; use /explain-diff for a teaching walkthrough.
Resolve the diff
$1 |
Scope |
|---|---|
| Branch | Working tree compared with that branch |
| Commit | git show <commit> |
HEAD |
Unstaged and staged changes |
| PR number | gh pr diff <number> |
| Range | git diff <range> |
| Omitted | Working tree compared with main; resolve the repository's default branch if absent |
Gather evidence
- Read the diff,
--stat, and--name-status, then the changed functions and surrounding callers needed to establish behavior. - Inspect affected public APIs, tests, configuration, documentation, and migrations.
- Read commit/PR descriptions, relevant plans, and available conversation history for recorded rationale. Separate observed behavior from inference; do not invent rejected alternatives.
- Keep a fact sheet mapping each displayed claim and quantity to command output or file:line. Mark unresolved claims as uncertain.
Compose the review
Lead with the concrete behavior change and its consequence. Give findings priority: each names a trigger, impact, source location, and possible correction. Report material uncertainty and validation gaps. Omit empty categories and generic praise.
Add only sections that help a reviewer:
- Matching before/after examples or diagrams for changed behavior. Preserve node names and layout direction between versions.
- A compact file/change table when scope needs explanation.
- Validation evidence describing exercised behavior and gaps, rather than test-count tiles.
- Recorded decisions, required migrations, and non-obvious contracts needed for follow-up work.
Use DiagramCanvas for supported layouts and follow cards/web-diagram.md for specialized diagrams. Keep before/after labels explicit; color may reinforce them. Default to the Lieflat-inspired preset, with open sections, readable snippets, and ruled tables. Do not add a KPI dashboard, housekeeping badges, or confidence meters.
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 · -39 lines · -4 tokens per session bca2b98d1094
- 1mo ago First seen · 79 lines · 16 tokens per session scan A 9f4d33e4606f
diff-review is a command published in the GitHub repository theclaymethod/artifacture (3 stars, last pushed 5d ago), licensed MIT. It adds 12 tokens to every session and 475 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 2026-08-31.
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.