Borrowing it
Nothing to install: this file belongs to sabbour/agentweaver. 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/sabbour/agentweaver/dev/.github/skills/docs-diagram-audit/SKILL.mdgit clone --depth 1 https://github.com/sabbour/agentweaverWrote 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/sabbour/agentweaver/docs-diagram-audit)<a href="https://agentmods.dev/skills/sabbour/agentweaver/docs-diagram-audit"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/docs-diagram-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/sabbour/agentweaver/docs-diagram-audit"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/docs-diagram-audit.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 | $0.00045 | $0.01334 |
| Opus 5.5 | $0.00018 | $0.00534 |
| Sonnet 5.5 | $0.00009 | $0.00267 |
| Haiku 4.5 | $0.00005 | $0.00133 |
Grade A, and why
docs-diagram-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 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit the Agentweaver documentation diagram catalog
Run this skill on demand for a repository-wide diagram audit or whenever a documentation
change may introduce, update, invalidate, consolidate, or remove architectural/process
visuals. This is a docs-only workflow. Do not change shipped product surfaces, runtime
APIs, product routing, packages/Agentweaver.Squad workflow definitions, product behavior,
or root dependencies needed outside documentation.
Read:
CONTRIBUTING.md;docs/guide/diagram-authoring.md;docs/diagrams/README.md;references/audit-checklist.md;references/audit-report.schema.json.
Evidence hierarchy
Research the repository implementation, configuration, tests, subject matter, and current written documentation as ground truth. Existing diagrams are legacy artifacts to assess, not factual evidence. When a diagram conflicts with current code or docs, the diagram is wrong.
1. Create a complete machine inventory
Run:
python .github/skills/docs-diagram-audit/scripts/diagram_audit.py discover `
--repo . --output docs-diagram-audit.json
The scan inventories every:
- source under
docs/diagrams/src/; - PNG and hash under
docs/diagrams/; - Markdown reference to a documentation diagram;
- missing, ambiguous, or unreferenced artifact.
Refreshing an existing report preserves reviewed dispositions, ownership, evidence, status, path-change history, and tombstone records for removed/reused/merged diagrams and concepts that no longer exist on disk. Do not edit diagrams during discovery.
2. Orchestrate GPT-6 Astra research
Use GPT-6 Astra for the audit coordinator's research workers and for downstream diagram
work. Partition the inventory into independent docs areas such as guide, deep-dive,
experience, reference, and shared.
For each area, launch a bounded GPT-6 Astra research agent that:
- reads current repository sources and current written docs;
- identifies the concepts the area must explain;
- maps legacy diagrams to those concepts;
- reports duplication, contradictions, stale visuals, missing coverage, and reusable canonical candidates;
- returns file/line evidence for every recommendation.
What ships with it
9 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.
- evals/evals.json 2.4 KB
- references/audit-checklist.md 1.8 KB
- references/audit-report.schema.json 6.7 KB
- reports/area-research.schema.json 3.6 KB
- reports/coverage.schema.json 8.0 KB
- reports/reconciliation.schema.json 2.2 KB
- scripts/__pycache__/diagram_audit.cpython-314.pyc 29 KB
- scripts/diagram_audit.py 19 KB runs code
- tests/test_diagram_audit.py 12 KB runs code
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 Changed · +3 lines 1881ad2dbcd5
- 1mo ago First seen · 154 lines · 45 tokens per session scan A a0e731c1f0a1
docs-diagram-audit is a skill published in the GitHub repository sabbour/agentweaver (7 stars, last pushed today), licensed MIT. It adds 45 tokens to every session and 1,334 once invoked, about $0.0002 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 2026-09-15.
Other skills, from other repositories
ui-design-source
Use this skill when the user provides Figma material, design-export files, screenshots of design tools, PDFs, JSON, existing HTML or other UI source code, or asks for design-to-HTML/code fidelity. It adapts OpenDesign/Figma handoff discipline for UIDesigner without requiring a live source runtime.
design-system-importer
Use this when COMPOSE or an AUTO compose segment has any external reference media or style source: a reference image, reference video, DESIGN.md, brand guide, screenshot, existing website, design notes, or an explicit named visual direction.
ui-design-system
Use this skill when creating, extending, or auditing a product UI system. It adapts Better Design-style design-system discipline without requiring an external runtime package.
ui-controls-accessibility
Before rendering, turn every explicitly requested workflow outcome into a compact ledger: user outcome -> triggering control/event -> rendered state branch -> recovery/next action. Success and failure are separate outcomes. When a backend is unavailable but the outcome can be modeled locally, make both outcomes…
product-ui
Use this skill when UI design and UI implementation should happen together. It turns product context into usable frontend screens, components, layout decisions, design-system choices, accessibility rules, and visual polish.
image-canvas
Read this private ImageStudio skill only after route lock when the result has multiple meaningful visual regions, an explicit reading order, exact layout constraints, or references bound to regions. Skip it for a simple single-region image. If art direction is also needed, establish it with image-craft before…