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/docsgit 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 | $0.00000 | $0.02247 |
| Opus 5 | $0.00000 | $0.01123 |
| Sonnet 5 | $0.00000 | $0.00449 |
| Haiku 4.5 | $0.00000 | $0.00225 |
Grade A, and why
docs 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 — 230 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Commands
TL;DR (30 seconds)
- What: 25 smart documentation commands from generation to ADHD-friendly enhancement
- Why: Automate docs updates, validation, and website optimization with one command
- How: Use
/craft:docs:update --interactivefor category-level prompts (NEW v2.7.0)- Next: Try
/craft:docs:update --interactive --dry-runto preview what would change
Smart documentation generation, validation, and enhancement - 48 commands.
Which Docs Command for What
| Scenario | Command | What It Does |
|---|---|---|
| "Update everything after changes" | /craft:docs:update |
Full cycle: detect → generate → validate → changelog |
| "What docs need updating?" | /folio:docs:sync |
Detection only — reports what's stale |
| "Are my docs valid?" | /folio:docs:check |
Validates links + nav + staleness + mermaid, auto-fixes |
| "Fix markdown formatting" | /folio:docs:lint |
Markdownlint with auto-fix |
| "Check only broken links" | /folio:docs:check-links |
Internal link validation with .linkcheck-ignore |
| "Update CLAUDE.md" | claude-md-lifecycle skill |
Sync CLAUDE.md with project state (folded into a skill, v4 consolidation) |
| "Update changelog" | /craft:docs:changelog |
Generate entries from git commits |
| "Add page to nav" | /folio:docs:nav-update |
Update mkdocs.yml navigation |
Decision flow:
- After writing code →
/craft:docs:update(does everything) - Before committing →
/folio:docs:check(validates) - PR merged to dev →
/craft:docs:update --post-merge(auto-fix pipeline) - Just want to check →
/folio:docs:sync(detection only, no changes)
Super Commands
/craft:docs:update
Smart-Full cycle with Interactive Mode (v2.7.0): 9-category detection with category-level prompts
/craft:docs:update --interactive # Category-level prompts (9 categories)
/craft:docs:update --category=version_refs # Update only version references
/craft:docs:update --interactive --dry-run # Preview without applying changes
/craft:docs:update --auto-yes # Batch mode (no prompts)
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 · 230 lines · 0 tokens per session scan A c5ea97dd947e
docs is a command published in the GitHub repository Data-Wise/craft (4 stars, last pushed 16d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,247 tokens. 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.