Strands Agents is an open-source SDK for building and running AI agents in Python and TypeScript. Developers use it to create agents with model providers, tools, lifecycle controls, memory, sessions, streaming, tracing, and evaluations, and the catalogue includes add-ons for its agent-building workflow.
Borrowing it
Nothing to install: this file belongs to strands-agents/harness-sdk. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/strands-agents/harness-sdk/main/.agents/skills/docs-audit/SKILL.mdgit clone --depth 1 https://github.com/strands-agents/harness-sdkWrote 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/strands-agents/harness-sdk/docs-audit)<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/docs-audit"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-audit/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/strands-agents/harness-sdk/docs-audit"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-audit.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00079 | $0.01313 |
| Opus 5.5 | $0.00032 | $0.00525 |
| Sonnet 5.5 | $0.00016 | $0.00263 |
| Haiku 4.5 | $0.00008 | $0.00131 |
Grade A, and why
docs-audit 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 9d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Documentation Audit
Assess an existing documentation page. Produces a structured assessment with specific improvement recommendations.
How this differs from docs-reviewer: The docs-reviewer is a voice/style gate for drafts in progress (runs at the end of docs-writer). The docs-audit is an assessment tool for published pages: it checks accuracy against SDK source, identifies content gaps, and optionally compares against competitor docs. Use docs-audit to decide what needs work; use docs-reviewer to verify that a draft is ready to ship. For a line-by-line check that every code example and prose claim is true against the source, use docs-verifier.
When to Use
- Before rewriting a doc page (understand current state first)
- When community signals point to confusion around a topic
- During periodic docs health checks
- When comparing Strands docs to competitor docs on the same topic
Inputs
- Target page: File path in
site/src/content/docs/or published URL - Content type: If known. If not, classify it first.
- Context (optional): Community signals, GitHub issues, or specific concerns
Process
Step 1: Fetch and classify
Read the source file from site/src/content/docs/ in this repo. If you need the published version and have web access, fetch from strandsagents.com.
Classify the content type (tutorial, howto, reference, explanation, mixed). Note: "mixed" is itself a finding. Pages that mix types are the most common structural problem.
Step 2: Voice stack review
Walk through each layer of the voice stack defined in ../../references/voice-guide.md against this page:
- Structure — Does each section answer exactly one question? Are there sections that mix concerns?
- Framing — Do section openings lead with the developer's goal, or with API descriptions?
- Register — Does the tone match the content type? Flag tutorial/reference mismatches.
- Hard constraints — Check for banned phrases, passive voice, hedging, terminology violations.
- Authenticity — Does the page have structural variety and visible editorial choices?
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.
- 9d ago Changed f1c2c15e539d
- 2mo ago First seen · 115 lines · 79 tokens per session scan A 5978c6c67eab
docs-audit is a skill published in the GitHub repository strands-agents/harness-sdk (8,996 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 1,313 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
returns-policy
Answer return, refund, and warranty questions for electronics. Use when the user mentions returns, refunds, RMAs, warranty coverage, damaged items, or opened packaging.
technical-troubleshooting
Provide setup, troubleshooting, and maintenance guidance. Use when the user reports a device that won't power on, connectivity issues, setup questions, overheating, or maintenance concerns.
agentscope-java
Expert Java developer skill for AgentScope Java framework - a reactive, message-driven multi-agent system built on Project Reactor. Use when working with reactive programming, LLM integration, agent orchestration, multi-agent systems, or when the user mentions AgentScope, ReActAgent, Mono/Flux, Project Reactor, or…
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.
synthesize-report
Produces a citation-grounded summary across one or more workspace source files for summaries, briefings, literature reviews, or comparisons.
data-analysis
Statistical data analysis skill — use when the user asks to analyze numbers, compute statistics, or summarize datasets.