harness-sdk: Skill for Claude Code

.agents/skills/docs-diagrams/SKILL.md

docs-diagrams is a skill for Claude Code, Codex from strands-agents/harness-sdk. It costs 70 tokens per session (932 once invoked), scanned A, original, Apache-2.0.

A design and implementation guide for diagrams on the Strands documentation site. It covers choosing the right diagram type, planning the story, and creating theme-aware SVG images that match the surrounding documentation.

In plain words
What is it for?
It helps create or review diagrams for documentation, including flowcharts, loops, sequences, and state machines, and place them in the site's asset structure.
Why use it?
It prevents diagrams from using inconsistent terms, unclear layouts, or visual styles that do not fit the site. It also helps decide when a table or paragraph would explain the idea better.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: installed under .agents/ (shared by several agents).

This is strands-agents/harness-sdk's own configuration. It tells Claude Code and Codex how to work on harness-sdk itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything harness-sdk configures →

About the project

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.

strands-agents/harness-sdk · 8,996 stars · on GitHub · strandsagents.com

Reuse

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.

Copy the file
curl -O https://raw.githubusercontent.com/strands-agents/harness-sdk/main/.agents/skills/docs-diagrams/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/strands-agents/harness-sdk

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 docs-diagrams

README.md
[![agentmods](https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-diagrams/github.svg)](https://agentmods.dev/skills/strands-agents/harness-sdk/docs-diagrams)
Your own site
<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/docs-diagrams"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-diagrams/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 docs-diagrams

Your own site · 80×15
<a href="https://agentmods.dev/skills/strands-agents/harness-sdk/docs-diagrams"><img src="https://agentmods.dev/badge/skills/strands-agents/harness-sdk/docs-diagrams.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 932 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.00932
Opus 5.5 $0.00028 $0.00373
Sonnet 5.5 $0.00014 $0.00186
Haiku 4.5 $0.00007 $0.00093

Measured 15d ago against content hash 9c6d9e7fce83, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

docs-diagrams scanned grade A with 1 finding 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 15d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (screenshot.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -s http://localhost:4321/docs/<page-path>/index.md | grep -A1 'Diagram:'
.agents/skills/docs-diagrams/SKILL.md · 97 lines

How it starts

The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Docs Diagrams

Create clear, editorial diagrams for the docs in the Strands brand. The rules are in ../../references/diagrams.md. Read it fully before drawing.

Inputs

  • Page: the .mdx file the diagram belongs to (required)
  • Source: the concept to illustrate

Workflow

1. Read the page

Read the prose around where the diagram goes. The diagram must match the text: the same terms, phase names, and order. Check terms against ../../references/terminology.md.

2. Decide, then state the plan

Before you write any SVG, tell the user:

  • The story: one sentence saying what the reader should take away.
  • The type: loop, fan-out, sequence, flowchart, state machine, and so on. Say why it fits the story.
  • Cuts: what you're removing from the source and why. Deletion is usually the best edit.
  • Focal: which one or two elements get the accent.

If a table or paragraph would do the job better, say so and don't draw.

3. Draw

  1. Create site/src/assets/diagrams/<concept-name>.svg. Start from the template in the reference.

  2. Lay it out on paper first. Compute box widths from the text-width estimate and keep every coordinate on the 4px grid.

  3. Write the file in paint order: zones → edges → labels → nodes. Use classes only, with no colors or styles in the SVG.

  4. Add the component to the page:

    import Diagram from '@components/Diagram.astro'
    
    <Diagram name="concept-name" alt="Full prose description of the diagram." />
    

    Put the import after the frontmatter, with the page's other imports.

4. Look at it

You haven't finished until you've looked at the rendered diagram in both themes.

npm install && (cd site && npm ci)                    # once, from the repo root
(cd site && npm run dev > /tmp/site-dev.log 2>&1 &)   # once; leave it running (~35s cold start)
node .agents/skills/docs-diagrams/screenshot.mjs /docs/<page-path>/   # from the repo root

The script waits up to 90s for the dev server. It captures diagrams in inactive language tabs too, and waits for Mermaid to finish rendering. If Chromium isn't installed, run npx playwright install chromium. Set PLAYWRIGHT_CHROMIUM_EXECUTABLE to use a specific browser binary.

Read the full file on GitHub · 97 lines

Files

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.

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. 15d ago First seen · 97 lines · 70 tokens per session scan A 9c6d9e7fce83

Subscribe to this mod's changes

docs-diagrams is a skill published in the GitHub repository strands-agents/harness-sdk (8,996 stars, last pushed today), licensed Apache-2.0. It adds 70 tokens to every session and 932 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-15.