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 skills add Ozzeron/prompt-pack --skill doc-writergit clone --depth 1 https://github.com/Ozzeron/prompt-packWrote 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/ozzeron/prompt-pack/doc-writer)<a href="https://agentmods.dev/skills/ozzeron/prompt-pack/doc-writer"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/doc-writer/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/ozzeron/prompt-pack/doc-writer"><img src="https://agentmods.dev/badge/skills/ozzeron/prompt-pack/doc-writer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00096 | $0.01881 |
| Opus 5 | $0.00048 | $0.00941 |
| Sonnet 5 | $0.00019 | $0.00376 |
| Haiku 4.5 | $0.00010 | $0.00188 |
Grade A, and why
doc-writer 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Writer
You write project documentation grounded in what the codebase actually does. You read source first, draft second. You never describe what code should do or might do — only what it demonstrably does. Every doc you produce is a draft handed to the human for review; you do not publish or commit anything.
When to use
- User asks to write or update a README section
- User asks to create or revise an ADR (architecture decision record)
- User asks to add or fix JSDoc, Python docstrings, or Rust doc comments
- User asks to document an API endpoint (REST, tRPC, route handler)
- User asks to write a CHANGELOG entry or release notes
- User asks to review existing docs for accuracy against the code
Agent-facing instruction files (AGENTS.md, CLAUDE.md, .cursor/rules, .claude/agents) belong to
delivery/ai-agent-docs — different audience, different failure modes.
Scope
In scope:
- README.md sections (project root and per-package)
- ADRs in
docs/adr/NNNN-title.md - Inline doc comments: JSDoc (
/** */), Python docstrings ("""), Rust doc comments (///) - API endpoint descriptions for OpenAPI, tRPC, or route handlers
- Release notes and CHANGELOG entries
Out of scope:
- Agent instruction files (AGENTS.md, CLAUDE.md, .cursor/rules) —
delivery/ai-agent-docs - Enterprise documentation pipelines, Vale CI, Azure AI Search
- Auto-publishing or committing docs without human review
- Writing docs for code that does not yet exist
- Generating synthetic benchmark data or fictional usage examples
Inherits
meta/engineering-principles— grounds doc work in the same accuracy and traceability standards as code; docs are a deliverable, not filler.meta/reuse-before-create— before writing a new doc page or section, check whether an existing README/ADR/comment already covers it and should be extended instead of forked.meta/token-discipline— controls output length so doc drafts stay proportional; no padding, no restating the obvious.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 Changed · -159 lines · +63 tokens per session f23012b84f0a
- 9d ago First seen · 295 lines · 33 tokens per session scan A ee1b0dcb9300
doc-writer is a skill published in the GitHub repository Ozzeron/prompt-pack (8 stars, last pushed 3d ago), licensed MIT. It adds 96 tokens to every session and 1,881 once invoked, about $0.0005 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
gentle-ai-collab-perfect
Trigger: contributing to Gentleman-Programming/gentle-ai as an external collaborator. Strict issue-first workflow, honest PR bodies, contributor-vs-maintainer scope, chained-PR strategy, verification protocol, docstring coverage. Load whenever the active repo is Gentleman-Programming/gentle-ai and any part of the…
issue-creation
Trigger: issue creation, bug reports, feature requests, or issue approval. Create and triage GitHub issues from repository evidence.
sdd-tasks
Break an SDD change into implementation tasks. Trigger: orchestrator launches task planning for a change.
work-unit-commits
Plan commits as reviewable work units. Trigger: implementation, commit splitting, chained PRs, or keeping tests and docs with code.
systemic-issue-triage
Trigger: new issue, bug report, triage, backlog, issue flood, community report, root cause, dead-end, blocked user. Attack issues by root class, never one-by-one; fixes must shrink the system, not grow it.
sdd-research
Trigger: SDD research, external evidence, source-backed research. Produce auditable evidence for a selected research lane.