Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/WangChangxin0809/repo-agent-harnessnpx agentmods add skills/wangchangxin0809/repo-agent-harness/writing-github-docsWrote 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/wangchangxin0809/repo-agent-harness/writing-github-docs)<a href="https://agentmods.dev/skills/wangchangxin0809/repo-agent-harness/writing-github-docs"><img src="https://agentmods.dev/badge/skills/wangchangxin0809/repo-agent-harness/writing-github-docs/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/wangchangxin0809/repo-agent-harness/writing-github-docs"><img src="https://agentmods.dev/badge/skills/wangchangxin0809/repo-agent-harness/writing-github-docs.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 | $0.00123 | $0.01760 |
| Opus 5.5 | $0.00049 | $0.00704 |
| Sonnet 5.5 | $0.00025 | $0.00352 |
| Haiku 4.5 | $0.00012 | $0.00176 |
Grade A, and why
writing-github-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 1mo 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
The repository's public face
Three documents answering three different questions. Mixing them is the expensive mistake in this category, because the result reads complete.
| File | Answers | Reader | Failure mode |
|---|---|---|---|
README.md |
What is this, and how do I run it | Someone passing through | Becomes a shrunken architecture document |
CONTRIBUTING.md |
How do I take part, and what do you want | Someone about to change it | Becomes a second quick start |
| Community health | Conduct, disclosure, licence, templates | The platform, and outside arrivals | Missing — and GitHub publishes the gap for you |
Writing CONTRIBUTING as a second quick start is the standard failure. It reads fine: install the dependencies, run it, here is the directory layout. And every single thing that actually stops a contributor is absent — who reviews their pull request, how long before anyone replies, what kind of change will simply not be accepted, where to send a vulnerability. Unable to answer those, they guess, or they leave.
These files need conventions of their own
docs/ conventions are designed for someone already inside: a scope header
answers "does this document cover my situation", a routing table answers "which
one do I read", immutability answers "is this still current". The public face
has none of those problems. Its reader has a repository URL and thirty seconds.
Adding a "does not cover" section to a README applies internal governance to a
problem that does not exist there.
In exchange it has a constraint docs/ does not: GitHub renders it. File
name, location, and in places even heading level change what the platform does —
SECURITY.md becomes the "Report a vulnerability" button, CODE_OF_CONDUCT.md
appears in the community profile, .github/ISSUE_TEMPLATE/*.yml replaces the
blank issue box. Getting the path wrong is not a style problem; the feature
silently does not appear.
README
Ten sections. Take the content of each from a document that already exists in
this repository, and note where you took it from. A section you have to invent
is a document the repository is missing — record that in
docs/exec-plans/tech-debt-tracker.md rather than writing plausible text.
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.
- 1mo ago First seen · 138 lines · 123 tokens per session scan A db21ee827b18
writing-github-docs is a skill published in the GitHub repository WangChangxin0809/repo-agent-harness (2 stars, last pushed 1mo ago), licensed MIT. It adds 123 tokens to every session and 1,760 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
han-release
Cut a Han release: update CHANGELOG.md with the changes since the last release, bump and tag every plugin that changed as {plugin-name}--v{version} so a version-constrained dependency can resolve, and publish a GitHub release crediting every merged pull request and closed issue to the people behind it. Use when…
han-update-documentation
Update Han plugin documentation so every skill, agent, guidance doc, index, and cross-reference is current and accurate. On a non-default branch, scopes the pass to entities the branch actually touched. On the default branch, performs a full documentation sweep across the whole plugin. Use when updating, refreshing…
atlas-changelog
Maintain per-repo and cross-repo changelogs — append structured entries after agent work. Use when asked to "log this change", "update changelog", "what changed", "change history".
ship-item
Ship a plan/todo item in a documentation-led repo — run the verify gate, integrate per the repo's model (fast-forward or PR), git mv todo→done with a shipped footer, advance the owning ADR(s) to Implemented, and regenerate INDEX. Use when the user says "ship this", "complete the plan item", "mark done", or "close out…
workspace-setup
Create or deliberately adopt a multi-repository Docflow WORKSPACE with a registry and portable memory. Use for workspace-setup or establishing a workspace home. NOT for bootstrapping a member repository, orientation, planning an outcome or executing assignments.
workspace-sync
Reconcile returned WORKSPACE receipts and maintain delivery observations from checked native evidence, observing member pull requests, merges, required checks, plan todo-to-done moves and branch heads, then refreshing INDEX. Use for workspace-sync or updating a workspace after native work, whether or not this…