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/drafthq/draft/documentationnpx skills add drafthq/draft --skill documentationgit clone --depth 1 https://github.com/drafthq/draftWhat 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 | $0.00033 | $0.01424 |
| Opus 5 | $0.00016 | $0.00712 |
| Sonnet 5 | $0.00007 | $0.00285 |
| Haiku 4.5 | $0.00003 | $0.00142 |
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 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 — 209 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation
You are generating or updating technical documentation for this project using structured writing principles.
Red Flags — STOP if you're
- Writing docs without reading the code first
- Duplicating information that exists elsewhere (link instead)
- Writing docs for internal implementation details (only public interfaces)
- Ignoring the target audience (developer vs operator vs new hire)
- Generating a wall of text without structure or examples
Write for the reader. Link don't duplicate. Show don't tell.
Pre-Check
- Check for Draft context:
ls draft/ 2>/dev/null
If draft/ doesn't exist, this skill works standalone — generate docs from code analysis.
- Follow the base procedure in
core/shared/draft-context-loading.md.
Step 1: Parse Arguments
/draft:documentation readme— Generate or update project README/draft:documentation runbook <service>— Operations runbook for a service/draft:documentation api <module>— API documentation for a module/draft:documentation onboarding— New developer onboarding guide/draft:documentation(no args) — Interactive: ask what type of documentation
Step 2: Gather Source Material
README Mode
- Read existing
README.md(if any) - Read
draft/product.md— Product vision, users, goals - Read
draft/tech-stack.md— Technologies, setup requirements - Read
draft/workflow.md— Development workflow, commands - Scan for
Makefile,package.json,pyproject.toml— Build/run commands
Runbook Mode
- Read
draft/architecture.mdordraft/.ai-context.md— Service topology, dependencies - Read
draft/workflow.md— Deployment conventions - Read
draft/tech-stack.md— Infrastructure details - If GitHub MCP available: check recent deployment changes
- If Jira MCP available: check recent incident tickets for the service
API Mode
- Read source code for public interfaces, exported functions, API routes
- Read existing API docs (Swagger, OpenAPI, JSDoc, docstrings)
- Read
draft/architecture.md— API conventions, data models - Read
draft/tech-stack.md— API framework details
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 · 209 lines · 33 tokens per session scan A 52b6534825c5
documentation is a skill published in the GitHub repository drafthq/draft (40 stars, last pushed 13d ago), licensed MIT. It adds 33 tokens to every session and 1,424 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 2026-08-30.
Other skills, from other repositories
memorix-memory
Use when prior workspace context, past decisions, solved bugs, handoff state, or durable project knowledge would help a coding task.
memorix
Use when Claude Code needs Memorix shared memory, reasoning, Git Memory, mini-skills, session handoff, orchestration coordination, or integration troubleshooting.
memorix-mini-skills
Use when durable project knowledge, gotchas, workflows, or repeated fixes should become reusable agent guidance instead of ordinary memory.
memorix-orchestrate
Use when a main agent needs Memorix to coordinate explicit subagent work through tasks, handoffs, messages, file locks, or the orchestrate CLI.
memorix-reasoning
Use when a technical decision, trade-off, rejected alternative, architecture rationale, or design risk should be recorded or recovered.
memorix-troubleshooting
Use when Memorix MCP, setup, project binding, HTTP control plane, hooks, skills, or agent integration is missing, stale, or failing.