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 skills/scolladon/craft/documentationnpx skills add scolladon/craft --skill documentationgit clone --depth 1 https://github.com/scolladon/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 | $0.00032 | $0.00848 |
| Opus 5 | $0.00016 | $0.00424 |
| Sonnet 5 | $0.00006 | $0.00170 |
| Haiku 4.5 | $0.00003 | $0.00085 |
Grade A, and why
documentation 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 2d 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 — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.
craft:documentation
Preamble (always runs — non-overridable)
- Manifest read (lint if standalone). Probe:
backlog:declared? (else no backlog work); which doc pages the change actually affects — the affected-page floor is mechanical:(diff ∩ subjects) ∪ probe— the existing judgment probe (public surface, behaviour a page states) UNIONed with every living page whose declaredsubjectsthe diff matches (via the intention port'sconsult; seedocs/contributing/specs/intention.md). A coverage gap — a load-bearing changed scope matched by no page'ssubjects, underintention.covers— escalates via the blocker protocol{ unit, reason, ≤3 options }rather than silently passing.
Procedure (default body — a manifest override: replaces everything below)
Runs in parallel with the validation phase's background run.
- Pages — only if any are affected: spawn craft:docs-writer with the affected
page list + what changed per page, the design doc path as content source, the
commit message
docs(<slug>): refresh pages, and the context files. Page refresh/create routes through the intention port'srecord.docs-writerstays update-only — it never creates a new page; a coverage gap that implies a missing page is a human decision, escalated per the Preamble, never auto-created. No affected pages → skip honestly (run record). - Backlog tick — guarded by source (see
docs/contributing/specs/backlog.md):source: file— consultbacklog-writeaction (defaultalways, ADR-127; seedocs/contributing/specs/policy.mdfor surface semantics); then spawn craft:backlog-ticker with the exact entry line and the exact reference suffix. Accept ONLY if the diff touches exactly the expected line(s) — otherwise discard and do the one-line edit yourself.source: custom— consultexternal-sendaction (defaultask, ADR-127; seedocs/contributing/specs/policy.md); on proceed, runrefwith argv["complete", id, ...refs];id/refsare untrusted, passed as discrete arguments (never spliced into a shell string) andidvalidated against the source's id-form before invoking (see the spec's safe-invocation note). A non-zero exit is a blocker (never a silent tick-skip); idempotency is the custom script's documented contract (seedocs/contributing/specs/backlog.md), not framework-asserted.
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.
- 2d ago First seen · 55 lines · 32 tokens per session scan A 7ecc368197d5
documentation is a skill published in the GitHub repository scolladon/craft (2 stars, last pushed 14d ago), licensed MIT. It adds 32 tokens to every session and 848 once invoked, about $0.0002 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 skills, from other repositories
external-context
Invoke parallel document-specialist agents for external web searches and documentation lookup.
security-ownership-map
Analyze git repositories to build a security ownership topology (people-to-file), compute bus factor and sensitive-code ownership, and export CSV/JSON for graph databases and visualization. Trigger only when the user explicitly wants a security-oriented ownership or bus-factor analysis grounded in git history (for…
moai-ref-ui-polish
UI polish and interface-completion reference: the small visual details — concentric border radius, optical alignment, shadow-vs-border, motion easing, typography smoothing, tabular numbers, icon stroke weight, hit areas — that separate polished interfaces from generic ones. Agent-extending skill that amplifies…
cross-task-learner
Enable agent loops to learn from similar past tasks and share patterns across loops.
ralph-specum-requirements
This skill should be used only when the user explicitly asks to use $ralph-specum-requirements, or explicitly asks Ralph Specum in Codex to run the requirements phase.
devkit-create-command
Create a new slash command with AI-guided behavior definition.