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/data-wise/craft/checkgit clone --depth 1 https://github.com/Data-Wise/craftWhat 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 | $0.00008 | $0.02826 |
| Opus 5 | $0.00004 | $0.01413 |
| Sonnet 5 | $0.00002 | $0.00565 |
| Haiku 4.5 | $0.00001 | $0.00283 |
Grade A, and why
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 yesterday.
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 — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/craft:check - Universal Pre-flight
This command is a thin(ner) shim. The canonical decision logic — which validators run for which
--forcontext, mode budgets, follow-up routing on failure — lives in thepreflight-checkskill (skills/preflight-check/SKILL.md). This file keeps the parts that are invocation-specific and can't be deferred to skill-routing: the flag contract above, and the exact LLM-executable output format Claude must produce when this command runs (kept here perskills/code/command-skill-token-efficiency/SKILL.md's rule that anything the command always needs — even if skill-routing hasn't fired yet — stays in the command file).Scope note: the pre-consolidation version of this command also carried full per-language project-detection walls (Python/Node/R/Go check lists), an extensive "community validator marketplace" section, and duplicated ASCII dry-run mockups for every mode/context combination. That's illustrative/aspirational content, not unique behavior — the skill's
--for/mode tables already capture the decision logic, and.claude-plugin/skills/validation/*.mdown the actual per-validator implementation. Dropped rather than ported; see the skill for anything that looks missing.
Usage
/craft:check # Quick validation
/craft:check thorough # Deep validation
/craft:check --for commit # Pre-commit checks
/craft:check --for pr # Pre-PR checks
/craft:check --for release # Pre-release checks
/craft:check --dry-run # Preview checks
/craft:check -n # Preview checks
/craft:check --context # Output session context only
Execution Behavior (MANDATORY)
When this command runs, Claude MUST follow these steps in order. Do NOT skip any step or proceed without showing the plan first.
Step 0: Show Check Plan
Before running ANY checks, display what will be checked:
Pre-flight Check Plan:
Project: <project-name> (<project-type>)
Mode: <mode>
Branch: <current-branch>
Guard: <protection-status>
Context: <for-value or "general">
Checks to run:
1. <check-name> (<tool>)
2. <check-name> (<tool>)
...
N. <check-name> (<tool>)
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.
- yesterday First seen · 316 lines · 8 tokens per session scan A a4daf25b429c
check is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It adds 8 tokens to every session and 2,826 once invoked, about $0.0000 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 2026-08-31.
Other commands, from other repositories
readme-audit
Audit a README's reading flow by treating it as a conversion funnel. Every section is evaluated against a target reader and a terminal action. Produces a structured audit blueprint that feeds directly into /readme-restructure.
readme-restructure
Execute a /readme-audit blueprint. Rewrites the README to the evaluator → conversion → links structure and creates linked docs by extracting and reorganising existing content.
build-fix
Fix build and type failures with minimal diffs.
checkpoint
Record a verified checkpoint before the next phase.
doctor
Check the install surface for missing files and invalid manifests.
feature-dev
Drive a feature from plan to implementation to review.