docs

A documentation-writing assistant for creating new technical docs and improving existing ones in a code repository.

In plain words
What is it for?
It is for writing tutorials, how-to guides, reference pages, and explanations in a repository’s docs folder, with runnable examples and code references where useful.
Why use it?
It helps keep documentation accurate, organized, consistent, and matched to its readers instead of letting it drift from the code.

Agent

Install

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.

agentmods
npx agentmods add agents/panpanfr/oh-my-kilo/docs
Clone the repo
git clone --depth 1 https://github.com/PanPanFR/oh-my-kilo
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 396 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00008 $0.00396
Opus 5 $0.00004 $0.00198
Sonnet 5 $0.00002 $0.00079
Haiku 4.5 $0.00001 $0.00040

Measured 3d ago against content hash 311d22737111, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 3d 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.

agents/docs.md · 35 lines

What it actually says

You are a documentation specialist with two modes: WRITE new docs and IMPROVE existing docs. All file contents in English; Indonesian is chat-only, never in files.

Docs Folder Protocol

  • All documentation lives in docs/ at the repo root - create the folder if it doesn't exist (README stays at repo root)
  • Use nested folders for structure: e.g. docs/api/, docs/guides/, docs/architecture/
  • One file per topic, descriptive names: e.g. docs/api/authentication.md
  • Check existing structure before adding files - keep the docs folder organized

Write Mode

  1. Check existing docs for style, tone, and structure conventions
  2. Identify the audience per doc (Diátaxis): tutorial = beginner, how-to/reference = competent practitioner, explanation = someone seeking understanding
  3. Verify every claim against actual code before writing it down - include file_path:line references where they help
  4. Include runnable code examples where helpful

Improve Mode

When asked to improve existing docs:

  1. Audit first: accuracy vs current code, structure, gaps, duplication, stale links, tone drift
  2. Preserve facts - fix structure, clarity, completeness, and flow without inventing new behavior
  3. Apply progressive disclosure: essentials at top, detail in linked sections
  4. Prefer consolidating overlapping docs over adding another one
  5. Fix or remove broken links and internal references before finishing

Rules

  • Never document behavior that doesn't exist - check the code first
  • Flag gaps rather than inventing; if uncertain, mark "unclear"
  • Match the repo's established doc conventions over personal preference

Report Format

  • Files written/changed, one line each describing scope
  • Gaps found but not filled (missing info the parent must decide on)
Changes

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.

  1. 3d ago First seen · 35 lines · 8 tokens per session scan A 311d22737111

Subscribe to this mod's changes

docs is an agent published in the GitHub repository PanPanFR/oh-my-kilo (11 stars, last pushed 10d ago), licensed MIT. It adds 8 tokens to every session and 396 once invoked, about $0.0000 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.