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 skills add Canvas-LMS-MCP/canvas-teacher-mcp --skill gws-richdocgit clone --depth 1 https://github.com/Canvas-LMS-MCP/canvas-teacher-mcpWrote 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/canvas-lms-mcp/canvas-teacher-mcp/gws-richdoc)<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/gws-richdoc"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/gws-richdoc/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/canvas-lms-mcp/canvas-teacher-mcp/gws-richdoc"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/gws-richdoc.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 | $0.00097 | $0.02320 |
| Opus 5 | $0.00048 | $0.01160 |
| Sonnet 5 | $0.00019 | $0.00464 |
| Haiku 4.5 | $0.00010 | $0.00232 |
Grade A, and why
gws-richdoc 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 12d 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 — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gws-richdoc — Rich Google Doc, ONE fixed look
Why this exists: hand-writing the HTML each session made every doc look different (rainbow vs
navy badges, boxes present/absent, no spacing). The fix is a single deterministic generator:
build.py. You assemble a list of block specs and call build — the blocks, colors, fonts, spacing,
and code coloring are FIXED in code, so every session produces the same look.
RULE: never hand-author rich-doc HTML. Build the content as block specs and run
build.py. The only thing that changes between docs is the text, never the formatting.
Files
gws-richdoc/
├── SKILL.md (this — the rules + how to call build.py)
└── build.py (the fixed generator: block builders + import + refine + code coloring)
build.py EXISTS and is verified (built 2026-06-22). Architecture = HYBRID: AI = WHAT (raw input → block specs + content + post-import QA), build.py = HOW (final look; AI never restyles — that is what made every doc look different). Two entry points:
make(blocks, name, folder_id, code_mode)→ NEW doc (create gdoc → HTML-import → refine). Verified to match this master template; inlinefont-sizesurvives import.colorize_code_cell(doc_id, lang, mode, which)→ color code in an EXISTING doc in place (no re-import → images/edits preserved). Use for docs with images.Code coloring: shell (regex) + Python (stdlib
tokenize, no pygments; robust to broken code). Python docstring modes:mode="correct"(docstring = ONE string color, real-editor accurate) vsmode="pretty"(docstring inner re-tokenized & colored — reads like live code). New.pycreation is blocked by the code-gate hook → open via~/.claude/.code-gate. gws call shape:--params= URL/query (documentId),--json= body (requests).
- Visual master reference (Drive):
1UzJhVARxgVB_49KcJg5BxyqIxeKPTiJnf1iRDBEVt6I(the skill template deck). Open it to SEE the canonical look.build.pyreproduces it.
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.
- 12d ago First seen · 120 lines · 97 tokens per session scan A 0555d024e38e
gws-richdoc is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 97 tokens to every session and 2,320 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
baoyu-youtube-transcript
A tool for downloading the written captions, subtitles, chapter information, speaker labels, and cover image from a YouTube video using its URL or ID.
orbit-notion
Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…
instrument-data-to-allotrope
Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
read
Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…
overleaf-sync
A two-way connection between a local paper folder and Overleaf, a web-based LaTeX editor for writing research papers. It lets you move changes between the local files and the shared Overleaf project.