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 agentmods add skills/sabbour/agentweaver/agentweaver-docs-featurenpx skills add sabbour/agentweaver --skill agentweaver-docs-featuregit 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/agentweaver-docs-feature)<a href="https://agentmods.dev/skills/sabbour/agentweaver/agentweaver-docs-feature"><img src="https://agentmods.dev/badge/skills/sabbour/agentweaver/agentweaver-docs-feature.svg" alt="Measured on agentmods" 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 | $0.00105 | $0.02877 |
| Opus 5 | $0.00053 | $0.01438 |
| Sonnet 5 | $0.00021 | $0.00575 |
| Haiku 4.5 | $0.00011 | $0.00288 |
Grade A, and why
agentweaver-docs-feature 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Context
The Agentweaver docs site (docs/, VitePress) documents every feature across multiple facets. Documenting a feature well means touching all the facets that apply — not just one page — in a consistent, code-grounded way. This skill is the authoring playbook.
It is the companion to the docs-sync skill, which owns drift detection and generated docs (scripts/gen-docs.mjs, the MCP tool index, and the CI check). Use docs-feature to author a feature's docs; use docs-sync to keep generated/derived docs in sync. See .github/DOCS_SYNC.md for the generated-vs-curated split and the CI workflow.
Core principles (non-negotiable)
- CODE is the source of truth — not specs or markdown. Read the actual C# / TS before writing a single claim. Every factual statement (routes, DTO fields, config keys, defaults, status codes, conditions) must trace to a real
file:line. Do not paraphrasespecs/or older docs — they drift; the code does not. - Consistency. Match the existing page structure, tone, frontmatter, section ordering, and the three-page pattern (deep-dive / reference / experience) of comparable features.
- Build gate.
cd docs; npm run buildmust stay green before you're done. - Plan → execute → verify. When invoked on a feature, first emit a per-facet plan/checklist for that feature, then execute each applicable facet, then build-verify.
The doc-surface facets matrix
For a given feature, decide which facets apply, then do each. (Not every facet applies to every feature — a backend-only change may skip the landing card and screenshots.)
| # | Facet | Location | What to produce | Source to ground in |
|---|---|---|---|---|
| 1 | Deep Dive | docs/deep-dive/{feature}.md |
Concept + end-to-end flow + a mermaid diagram + a ## Source file table. |
The implementing C#/TS classes & services. |
| 2 | Reference | docs/reference/{feature}.md |
Terse routes table, DTO field tables, config keys, status codes — all from source. | *Endpoints.cs, DTO records, appsettings/config keys, apps/web/src/api/types.ts. |
| 3 | User Guide / Experience | docs/experience/{feature}.md |
Step-by-step user flow, "when available", "what to expect". | The web UI components (apps/web/src/pages/*, client.ts). |
| 4 | Screenshots | docs/public/screenshots/{name}.png (placeholder) + a row in docs/experience/screenshot-plan.md + a draft test in tests/e2e/screenshots.spec.ts |
Placeholder image, a plan row (file → page → route → click-path → what it shows), and a test.skip-guarded capture test. |
The real route + UI labels/aria-labels. |
| 5 | Landing card | docs/index.md features: list |
A feature card (title + details + See it in action → link) only if it's a headline / value-prop feature. |
The feature's user value. |
| 6 | Nav wiring | docs/.vitepress/config.ts |
Sidebar entry under the right group (Getting Started / User Guide / Deep Dive / Reference) + top-nav if it's a new section. | Existing sidebar groups. |
| 7 | Cross-links | The new pages and related existing pages | See also / Related reading links both ways. |
Related existing pages. |
| 8 | Diagrams | Inside the deep-dive (and others as needed) | Mermaid diagram following repo conventions (see below). | The real flow. |
| 9 | Generated docs | via node scripts/gen-docs.mjs |
If the feature adds MCP tools or API endpoints, regenerate the derived reference and commit it. CI --checks it. |
apps/Agentweaver.Mcp/Tools/*.cs, endpoints. Owned by docs-sync. |
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.
- 4d ago First seen · 112 lines · 105 tokens per session scan A a948338385a0
agentweaver-docs-feature is a skill published in the GitHub repository sabbour/agentweaver (5 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 2,877 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
mcaf-adr-writing
Create or update an ADR under docs/ADR/ for architectural decisions, dependency changes, data-model changes, or cross-cutting policy shifts. Use when the user asks to write, update, or document an ADR, record a design decision, capture architecture trade-offs, or justify a repo-wide technical policy.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
command-creator
This skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want to document a workflow as a reusable command. Essential for creating optimized, agent-executable slash commands with proper structure and best practices.
docx
Create/edit/inspect Word documents using available managed or host capabilities.
xlsx
Create/edit/analyze/verify spreadsheet workbooks including XLSX/CSV/TSV.
prd
Generates a Product Requirements Document from a natural language app description. Asks clarifying questions, researches similar apps, defines scope, stack, architecture, and produces a structured PRD that Archon can decompose into a campaign.