What is write-repo-doc?

A writing guide for internal documentation, such as guides, README sections, and files in a docs folder. It focuses on helping a newcomer act without already knowing the system's vocabulary or layout.

Use it to rewrite internal docs with a quick start, plain-language explanations, linked commands and schemas, and diagrams where needed. Read it when documenting a system for someone outside its original development context.

It reduces the guesswork caused by unexplained terms, missing setup steps, and links that point to the wrong files. It also makes documentation useful to both people and fresh agent sessions.

How bredmond1019/claude-sdk-rs configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to bredmond1019/claude-sdk-rs. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/bredmond1019/claude-sdk-rs/main/.agents/skills/write-repo-doc/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/bredmond1019/claude-sdk-rs

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/write-repo-doc/github.svg)](https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/write-repo-doc)

Your own site

<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/write-repo-doc"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/write-repo-doc/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/bredmond1019/claude-sdk-rs/write-repo-doc"><img src="https://agentmods.dev/badge/skills/bredmond1019/claude-sdk-rs/write-repo-doc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 110 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,434 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00110	$0.02434
Opus 5.5	$0.00044	$0.00974
Sonnet 5.5	$0.00022	$0.00487
Haiku 4.5	$0.00011	$0.00243

Measured 11d ago against content hash 6f7fd1d33127, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

write-repo-doc 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 11d 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/skills/write-repo-doc/SKILL.md · 200 lines

How it starts

The opening of the file, as written. The whole thing — 200 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing an internal doc

Governed by D72 (planning/decisions/D72-write-repo-doc-is-the-internal-docs-standard.md). How the corpus gets converted: D73 (…/D73-docs-upgrade-incrementally-through-close-out.md).

Who you are writing for

Brandon plans this system and approves every decision. He did not write the code — agents did. He cannot skim a hundred files at agent speed to reconstruct what a word means.

So the reader is: smart, invested, and missing the context the author has. They know the goal. They do not know your vocabulary, your file layout, or which of the three things you named is the one they should type.

A second reader matters just as much: a fresh agent session with no context. Every inline link you write is an edge it can follow instead of guessing. Under-linking costs it a search; a wrong link costs it a false belief.

The whole standard in one line: a good teacher would never write the doc you are about to write by default. Write the one they would.

Quickstart

Read the doc as a newcomer. Note every sentence you could not act on. That list is the work.
Put a Quickstart at the top — the literal commands, in order, that get someone from nothing to a result.
Open every section with one plain-English sentence saying what it is and why it exists, before any detail.
Link every command, script, schema and decision the first time you name it.
Explain or link every term a newcomer would not know.
Add a diagram if the shape is not obvious from prose.
Run the checklist at the bottom, then the gates.

The seven rules

1. Quickstart first, always

The first thing after the title is how to get started, not what the system is.

Real commands, copy-pasteable, in the order they are run.
Say where each is typed — a Claude Code slash command and a shell command look identical on the page and are not interchangeable. /begin-orchestration goes in Claude Code. python3 x.py goes in a terminal. Say which.
Then a short table of what must exist first, and what to do if it does not.

Read the full file on GitHub · 200 lines

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.

11d ago First seen · 200 lines · 110 tokens per session scan A 6f7fd1d33127

Subscribe to this mod's changes

write-repo-doc is a skill published in the GitHub repository bredmond1019/claude-sdk-rs (23 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 110 tokens to every session and 2,434 once invoked, about $0.0004 per session on Opus 5.5. 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 2026-10-26.

Writing and docs

write-repo-doc next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
write-repo-docbredmond1019/claude-sdk-rs	Skill	23	1mo ago	Apache-2.0	A	110	Claude Code, Codex
imagegenopenai/codex	Skill	133k	yesterday	Apache-2.0	A	113	Codex
playwright-climicrosoft/playwright	Skill	99k	yesterday	Apache-2.0	A	19	Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginners	Skill	79k	4d ago	MIT	A	200	Claude Code, Codex
systematic-debuggingobra/superpowers	Skill	313k	3d ago	MIT	A	21	Claude Code
next-cache-components-adoptionvercel/next.js	Skill	143k	today	MIT	A	95	Claude Code
next-partial-prefetching-adoptionvercel/next.js	Skill	143k	today	MIT	A	103	Claude Code

claude-sdk-rs: Skill for Claude Code