aih-betterdoc

aih-betterdoc is a skill for Claude Code, Codex from samartomar/ai-harness. It costs 113 tokens per session (2,325 once invoked), scanned A, original, Apache-2.0.

A documentation-writing and review workflow based on evidence and explicit claims.

In plain words
What is it for?
Use it for READMEs, guides, reference pages, architecture records, security documents, runbooks, changelogs, and release notes.
Why use it?
It helps keep public technical documentation accurate and prevents unsupported claims or private information from being published.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: $skill-name invocation.

Good fit Use it for READMEs, guides, reference pages, architecture records, security documents, runbooks, changelogs, and release notes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/samartomar/ai-harness/aih-betterdoc
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.

Any agent
npx skills add samartomar/ai-harness --skill aih-betterdoc
Clone the repo
git clone --depth 1 https://github.com/samartomar/ai-harness

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.

agentmods badge for aih-betterdoc

README.md
[![agentmods](https://agentmods.dev/badge/skills/samartomar/ai-harness/aih-betterdoc/github.svg)](https://agentmods.dev/skills/samartomar/ai-harness/aih-betterdoc)
Your own site
<a href="https://agentmods.dev/skills/samartomar/ai-harness/aih-betterdoc"><img src="https://agentmods.dev/badge/skills/samartomar/ai-harness/aih-betterdoc/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.

agentmods 80×15 button for aih-betterdoc

Your own site · 80×15
<a href="https://agentmods.dev/skills/samartomar/ai-harness/aih-betterdoc"><img src="https://agentmods.dev/badge/skills/samartomar/ai-harness/aih-betterdoc.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 113 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,325 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 5.1 $0.00113 $0.02325
Opus 5 $0.00056 $0.01162
Sonnet 5 $0.00023 $0.00465
Haiku 4.5 $0.00011 $0.00232

Measured 6d ago against content hash bc4769f4a56f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

aih-betterdoc 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 6d 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.

ai-coding/curated-skills/aih-betterdoc/SKILL.md · 301 lines

How it starts

The opening of the file, as written. The whole thing — 301 lines — stays where its author put it; the contents beside it link to each section on GitHub.

BetterDoc (ai-harness)

This is the project-curated, CLI-neutral copy of the BetterDoc skill distributed from packs/docs-quality/aih-betterdoc/. Load it through the repository's shared canon routing. Do not create per-client copies or run AIH to install, refresh, or validate it in this checkout.

BetterDoc improves documentation without weakening truth.

Use this skill when drafting, editing, reviewing, or restructuring public technical or product documentation. It does not authorize new product claims, private disclosures, implementation changes, publishing, or release actions.

Repository profile

Before editing public documentation, read:

  1. ai-coding/rules/doc-and-truth-homes.md for public/private truth routing.
  2. PUBLIC_DOCS_POLICY.md for prohibited material and claims discipline.
  3. The closest document-specific source of truth and the code, schemas, tests, generated artifacts, or CI evidence that support its claims.
  4. docs/CONTROL_MATRIX.md when the document describes controls, enforcement, or evidence surfaces.

This repository is public. Never copy strategy, competitive analysis, pricing, customer information, private roadmap sequencing, maintainer runbooks, private repository references, or session handoff text from the private companion into public documentation. Sanitize examples and label demo data as required by PUBLIC_DOCS_POLICY.md.

Never hand-edit generated or byte-locked documentation. Edit its renderer or source. Never run AIH against this checkout, including to lint, regenerate, or project documentation. Use direct repository checks such as npm run docs:lint, focused tests, and the validation commands named by the changed document's owning code.

Core rule

Do not trade correctness for smoothness.

A better document is:

  1. true,
  2. useful to the intended reader,
  3. scoped to what the source supports,
  4. easy to follow,
  5. clear and concise.

Clean prose is not enough. A polished unsupported claim is worse than a rough accurate sentence.

Read the full file on GitHub · 301 lines

Files

What ships with it

4 files 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.

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. 6d ago First seen · 301 lines · 113 tokens per session scan A bc4769f4a56f

Subscribe to this mod's changes

aih-betterdoc is a skill published in the GitHub repository samartomar/ai-harness (6 stars, last pushed yesterday), licensed Apache-2.0. It adds 113 tokens to every session and 2,325 once invoked, about $0.0006 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 2026-09-04.

Related

Other skills, from other repositories