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 vishalsachdev/canvas-mcp --skill canvas-peer-review-managergit clone --depth 1 https://github.com/vishalsachdev/canvas-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/vishalsachdev/canvas-mcp/canvas-peer-review-manager)<a href="https://agentmods.dev/skills/vishalsachdev/canvas-mcp/canvas-peer-review-manager"><img src="https://agentmods.dev/badge/skills/vishalsachdev/canvas-mcp/canvas-peer-review-manager/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/vishalsachdev/canvas-mcp/canvas-peer-review-manager"><img src="https://agentmods.dev/badge/skills/vishalsachdev/canvas-mcp/canvas-peer-review-manager.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00068 | $0.02396 |
| Opus 5.5 | $0.00027 | $0.00958 |
| Sonnet 5.5 | $0.00014 | $0.00479 |
| Haiku 4.5 | $0.00007 | $0.00240 |
Grade A, and why
canvas-peer-review-manager 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 — 227 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Peer Review Manager
A complete peer review management workflow for educators using Canvas LMS. Monitor completion, analyze quality, identify students who need follow-up, send reminders, and export data -- all through MCP tool calls against the Canvas API.
Prerequisites
- Canvas MCP server must be running and connected to the agent's MCP client (e.g., Claude Code, Cursor, Codex, OpenCode).
- The authenticated user must have an educator or instructor role in the target Canvas course.
- The assignment must have peer reviews enabled in Canvas (either manual or automatic assignment).
- FERPA-conscious handling: Set
ENABLE_DATA_ANONYMIZATION=truein the Canvas MCP server environment to anonymize supported student identity fields. When enabled, names render asStudent_xxxxxxxxhashes while preserving functional user IDs for messaging. This control does not by itself establish compliance.
Steps
1. Identify the Assignment
Ask the user which course and assignment to manage peer reviews for. Accept a course code, Canvas ID, or course name, plus an assignment name or ID.
If the user does not specify, prompt:
Which course and assignment would you like to check peer reviews for?
Use list_courses and list_assignments to help the user find the right identifiers.
2. Check Peer Review Completion
Call get_peer_review_completion_analytics with the course identifier and assignment ID. This returns:
- Overall completion rate (percentage)
- Number of students with all reviews complete, partial, and none complete
- Per-student breakdown showing completed vs. assigned reviews
Key data points to surface:
| Metric | What It Tells You |
|---|---|
| Completion rate | Overall health of the peer review cycle |
| "None complete" count | Students who haven't started -- highest priority for reminders |
| "Partial complete" count | Students who started but didn't finish |
| Per-student breakdown | Exactly who needs follow-up |
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 · -1 lines 5dff0035d357
- 1mo ago First seen · 228 lines · 68 tokens per session scan A e817ccc111e7
canvas-peer-review-manager is a skill published in the GitHub repository vishalsachdev/canvas-mcp (307 stars, last pushed today), licensed MIT. It adds 68 tokens to every session and 2,396 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
startups-page-generator
Deprecated compatibility entry for Startup Program Page construction. This page is now maintained in Pagina; install and use page-builder to build a new Startup Program Page.
education-program
When the user wants to plan, implement, or optimize student and education discount programs. Also use when the user mentions "student discount," "education discount," "student plan," "for students," ".edu discount," "academic pricing," "student verification," "SheerID," "UNiDAYS," or "education program." For startup…
creating-explainers
Use when creating an interactive explainer - a single self-contained HTML page with hand-built Canvas figures. Handles source-file explainers, topic-driven research explainers, and mixed intake where files provide the spine and research adds support. Trigger phrases include "make an explainer", "turn this paper into…
explaining-codebases
Use when creating an interactive explainer about a codebase, repository, or source files. Handles onboarding overviews, architecture maps, and deep-dives on real implementation paths. Trigger phrases include "explain this codebase", "interactive guide to this repo", "walk through how X works in the code", or…
behavioral-design
Applies behavioral science (COM-B, B=MAP, EAST, defaults) to change behavior in teams and organizations (employees, managers, or engineers adopting a practice or tool) and in product flows; plans rollouts, workshops, and presentations; never recommends a dark pattern or sludge. Triggers on "how do I get my team to X"…
zen-of-checkpickerupper
The Zen of CheckPickerUpper: twenty-one lines that judge designs, fixes, abstractions, types, structure, and questions, each expanded and traced to its source skill. Use when settling a design choice or an ambiguous question, choosing between options, judging whether a fix, abstraction, type, or layout is right, or…