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/plan-review)<a href="https://agentmods.dev/commands/theclaymethod/artifacture/plan-review"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/plan-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/plan-review"><img src="https://agentmods.dev/badge/commands/theclaymethod/artifacture/plan-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 | $0.00372 |
| Opus 5.5 | $0.00005 | $0.00149 |
| Sonnet 5.5 | $0.00002 | $0.00074 |
| Haiku 4.5 | $0.00001 | $0.00037 |
Grade A, and why
plan-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.
This is a copy
91% identical to plan-review — 92 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.
What it actually says
Load SKILL.md. Compare plan $1 with codebase $2, or the current directory when $2 is omitted.
Establish the evidence
- Read the plan: problem, proposed changes, reasoning, rejected alternatives, and scope.
- Inspect referenced files and affected callers, tests, configuration, types, schemas, and public APIs.
- Verify that referenced symbols exist and that the plan describes current behavior accurately.
- Map each proposed change to its dependencies and validation needs. Record claim sources as plan sections or file:line; mark unknowns explicitly.
Compose the review
Lead with the plan's intended behavior and the most consequential finding. Use as much structure as the evidence needs:
- Current and proposed behavior, with matching names and layout direction in comparison diagrams.
- Change-by-change discrepancies, omitted dependencies, and unsupported assumptions.
- Concrete risks: triggering condition, consequence, evidence, and mitigation. Include migration, rollback, concurrency, or ordering only where relevant.
- Recorded rationale and alternatives. An absent explanation is unknown, not an invitation to invent one.
- Existing validation and gaps that must be resolved before implementation.
- A short list of decisions or corrections needed to proceed.
Use cards/web-diagram.md for diagrams and cards/comparison-table.md for comparison tables. Default to the Lieflat-inspired preset. Show additions and removals with explicit labels; avoid glow, confidence badges, impact dashboards, invented line estimates, and empty Good/Bad/Ugly categories.
Author MDX/TSX and export to ~/.agent/diagrams/<slug>-plan-review.html. Complete references/verification.md, open the result, and return the source, HTML, final report, and remaining uncertainty.
$@
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 · -66 lines · -4 tokens per session 5e9f32fcc770
- 1mo ago First seen · 95 lines · 16 tokens per session scan A c73c60a0b519
plan-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 372 once invoked, about $0.0000 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to plan-review, differing in 92 lines, and is treated as a copy.
Other commands, from other repositories
learn
Force claude-smart to extract learnings from this session now.
prototype
You are building a proof-of-concept for the current Grainulator sprint. Read CLAUDE.md for sprint context and claims.json for existing research claims.
init
Install the formatters this repository needs, with every command visible before it runs.
genshijin-compress
A command for safely shortening Markdown or text files into the genshijin style.
dispatcher
Use when you want the orchestrator to pick the next repo to work on across your whole portfolio — it enumerates candidate repos below the confinement root, resolves free/busy from each repo's session.lock lease, ranks the FREE ones by backlog priority × staleness × readiness, recommends the single most worthwhile one…
standup
Show a daily standup summary with completed, in-progress, and blocked tasks across all active epics.