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 burin-labs/harn --skill harn-docsgit clone --depth 1 https://github.com/burin-labs/harnWrote 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/burin-labs/harn/harn-docs)<a href="https://agentmods.dev/skills/burin-labs/harn/harn-docs"><img src="https://agentmods.dev/badge/skills/burin-labs/harn/harn-docs.svg" alt="Measured on agentmods" 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 | $0.00027 | $0.01347 |
| Opus 5 | $0.00014 | $0.00674 |
| Sonnet 5 | $0.00005 | $0.00269 |
| Haiku 4.5 | $0.00003 | $0.00135 |
Grade A, and why
harn-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 7d 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 — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Write Harn developer documentation
Write for the developer who has a task. Pair this skill with [[harn-language]] for checked Harn examples, [[harn-testing]] for executable proof, and [[harn-product-quality]] for a complete user path.
Set the page contract
- Read the nearest
AGENTS.md, the publishing index, the glossary, and the source that owns the behavior. - Name the reader, their task, and a falsifier for each material claim.
- Give the page one Diátaxis purpose: tutorial, how-to, reference, or explanation.
- Split mixed-purpose pages and link them where the reader needs to switch.
- In Harn,
docs/src/SUMMARY.mdis the published index anddocs/src/concepts/glossary.mdowns public terms. - In Burin, read
site/src/content/README.mdbefore choosing a help-center category.
Draft from evidence
- Lead with the result or action.
- Use the exact command, type, state, default, limit, error, and path from source. Do not invent friendly aliases.
- Explain permissions, side effects, and recovery where they affect a choice.
- Put examples on the canonical product path and run them.
- Link the next local page inline. Link primary external sources for protocols, providers, model cards, licenses, and third-party setup.
- For current or comparative claims, inspect the peer page that serves the same developer task. Useful agent-framework checks include Flue's quickstart, agent guide, and event reference.
- State observed facts as facts. Mark inference and remove unsupported claims.
Edit the prose
Apply the current Slopwash rules. Where they are silent on a question of usage, the Google developer documentation style guide (CC BY 4.0) is the reference; the Microsoft writing style guide is the second opinion. Neither overrides a rule below.
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.
- 7d ago First seen · 129 lines · 27 tokens per session scan A ece3d6b674ce
harn-docs is a skill published in the GitHub repository burin-labs/harn (20 stars, last pushed yesterday), licensed Apache-2.0. It adds 27 tokens to every session and 1,347 once invoked, about $0.0001 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.
Other skills, from other repositories
translate
A translation tool for converting user-provided text between languages, with Chinese and English as the default pair.
agent-communication-protocol
Open protocol for AI agent interoperability enabling standardized communication between agents, applications, and humans across different frameworks.
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
gh-issue
Fetch a GitHub issue, create a branch, implement with TDD, and open a PR.
gh-issues
Walk over all open GitHub issues that are unassigned or assigned to the current user, and process each one via the /gh-issue skill, sequentially.
module-new
Scaffold a new Gacela module under src/php/ with Facade, Provider, and CLAUDE.md.