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 bruchris/canvas-lms-mcp --skill canvas-admin-rostergit clone --depth 1 https://github.com/bruchris/canvas-lms-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/bruchris/canvas-lms-mcp/canvas-admin-roster)<a href="https://agentmods.dev/skills/bruchris/canvas-lms-mcp/canvas-admin-roster"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-admin-roster/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/bruchris/canvas-lms-mcp/canvas-admin-roster"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-admin-roster.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 | $0.00000 | $0.02787 |
| Opus 5 | $0.00000 | $0.01393 |
| Sonnet 5 | $0.00000 | $0.00557 |
| Haiku 4.5 | $0.00000 | $0.00279 |
Grade A, and why
canvas-admin-roster 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 11d 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 — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Admin Roster
Admin-audience skill for inspecting the Canvas account tree and making targeted enrollment changes. Walks list_accounts → list_sub_accounts → list_account_courses / list_account_users so the agent paces itself instead of dumping the whole institution at once. Write paths (enroll_user, remove_enrollment) are explicitly gated by per-action confirmation and are clearly separated from the read paths.
Prerequisites
- Canvas MCP server must be running and connected.
- Admin Canvas token required. A teacher or TA token will return empty results from
list_accountsand 401/403 fromlist_sub_accounts,list_account_courses,list_account_users, andget_account_reports. If the user does not have an admin token, stop at Step 1 and tell them this skill needs an admin role on the relevant account. enroll_userandremove_enrollmentadditionally require permission to manage enrollments on the target course. A "subaccount admin" role may be able to read the account but not modify enrollments — the skill will surface a 403 if that happens.- Many admin endpoints expose institution-wide data. Only run this skill in a private session.
Steps
1. Discover the Accounts You Can See
Call list_accounts. This returns every account the authenticated admin has access to — in many institutions this is just the root account, but multi-tenant Canvas deployments can return several.
If the response is empty, the token does not have admin scope. Stop here and tell the user.
Show the user the accounts with their id, name, and parent_account_id:
ACCOUNTS YOU CAN ADMIN
• [1] Root Account (Big State University)
• [42] College of Engineering parent: 1
• [43] College of Liberal Arts parent: 1
2. Walk the Sub-Account Tree
Ask the user which account to drill into, or default to the root account.
For the chosen account, call list_sub_accounts with that account_id. This is shallow — it returns direct children only, not the full descendant tree. If the user wants to walk further down, repeat list_sub_accounts on each child sub-account they pick. Do not recurse the whole tree by default — large institutions can have hundreds of sub-accounts and you will burn quota.
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.
- 11d ago First seen · 171 lines · 0 tokens per session scan A e1fc718a8242
canvas-admin-roster is a skill published in the GitHub repository bruchris/canvas-lms-mcp (5 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,787 tokens. 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
education-expert
Expert-level education technology, learning management systems, and ed-tech platforms. Use when the user mentions edtech, lms, e learning, or assessment, or when the task involves Educational Technology or Standards.
emil-design-eng
This skill encodes Emil Kowalski's philosophy on UI polish, component design, animation decisions, and the invisible details that make software feel great.
humanizer
Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague…
apple-design
Apple's approach to interface design and fluid, physical motion, translated for the web. Use when building or reviewing gesture-driven UI, spring animations, drag/swipe/sheet interactions, momentum and interruptible transitions, translucent materials and depth, typography (optical sizing, tracking, leading)…
add-landing-template
Add a new org landing-page template to the ClassroomIO monorepo. Use when the user asks to "create/add a new landing template", "add a new template like X to the org landing pages", "build a new theme for the org landing page", or hands over a design reference (image, URL, prototype) for a new landing visual style.
animation-vocabulary
Reverse-lookup glossary that turns a vague description of a web animation or motion effect into its exact term ("the bouncy thing when a popover opens" → Pop in; "the iOS rubber-band scroll" → Rubber-banding). Use when the user asks "what's it called when…", or describes a motion effect without knowing its name and…