Borrowing it
Nothing to install: this file belongs to Smart-AI-Memory/attune-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/Smart-AI-Memory/attune-ai/main/.agents/skills/doc-gen/SKILL.mdgit clone --depth 1 https://github.com/Smart-AI-Memory/attune-aiWrote 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/skills/smart-ai-memory/attune-ai/doc-gen)<a href="https://agentmods.dev/skills/smart-ai-memory/attune-ai/doc-gen"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/doc-gen/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/skills/smart-ai-memory/attune-ai/doc-gen"><img src="https://agentmods.dev/badge/skills/smart-ai-memory/attune-ai/doc-gen.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00041 | $0.00786 |
| Opus 5 | $0.00020 | $0.00393 |
| Sonnet 5 | $0.00008 | $0.00157 |
| Haiku 4.5 | $0.00004 | $0.00079 |
Grade A, and why
doc-gen 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 5d 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 — 119 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Doc Gen
IMPORTANT: Start your response with a context preamble.
Call help_lookup(topic="doc-gen", mode="preamble") and
display the returned preamble text as a blockquote. Then
tell the user they can say "tell me more" for a step-by-step
guide, or answer the scoping questions below to proceed.
If the MCP call fails, fall back to:
Doc Gen — Generates documentation from your source code — docstrings, README sections, API references.
Scoping
Before running, ask:
- Target: "Which file or module needs documentation?"
- Type: "What kind of docs?"
- Docstrings — Add or update Google-style docstrings
- README — Generate a README section for a module
- API reference — Generate full API documentation
- Overview — High-level module explanation
MCP Tools
| Tool | What It Does |
|---|---|
doc_gen |
Generate documentation for a module |
doc_audit |
Check for stale or missing docs |
doc_orchestrator |
Full documentation maintenance pipeline |
Execution
Shared command workspace (preferred)
Open adapter doc-gen with the validated target and documentation type. Run
the bound read-only doc_audit action first and publish audit_result with
the exact proposed artifact paths. Present the proposal widget or Markdown;
only an explicitly confirmed apply_docs action authorizes those paths.
After doc_gen, publish generation_result with the exact files reported
from disk. The adapter hashes them independently and rejects writes outside or
different from the approved set. Run the returned doc-import-audit/symbol
reality probe and publish its exact command and outcome as
validation_result. A partial write or failed reality probe must say “did not
complete” and retain changed-file hashes for rollback. Preserve these gates
and receipts in compact text when the shared tools are unavailable.
For docstring generation:
doc_gen(source_path="<target module>")
For a full documentation audit first:
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.
- 5d ago Changed · +15 lines 616a356fcabb
- 8d ago First seen · 104 lines · 41 tokens per session scan A 663a74a08586
doc-gen is a skill published in the GitHub repository Smart-AI-Memory/attune-ai (10 stars, last pushed today), licensed Apache-2.0. It adds 41 tokens to every session and 786 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
eco-max
Maximum-savings variant of /eco - the same frugality rules PLUS a low reasoning-effort override for the invoked task. Use for routine chores (rename, small fix, quick question, boilerplate) when the user wants absolute minimum token spend; prefer plain /eco for hard or high-stakes work. Works in any language.
wiki-ingest
Ingest a source into the project wiki as OKF v0.2 markdown. Point at a file, PR, or doc and the wiki-curator extracts knowledge, writes YAML frontmatter, and updates relevant concept pages.
wiki-lint
Health-check the project wiki for OKF v0.2 conformance — missing frontmatter, missing type:, malformed index.md/log.md, stale pages past staleafter, broken cross-references, and coverage gaps.
run
Run a full pipeline for a task. Orchestrates roles through stages (standalone or HOTL-integrated).
ci-repair
Fix CI failures by fetching GitHub Actions logs, dispatching dev to fix, verifying locally, and pushing.
deepdive
Full specialist analysis via parallel agent dispatch. Researcher, Architect, and PM produce a prioritized report of what to build next (30-60s).