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-gradebook-auditgit 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-gradebook-audit)<a href="https://agentmods.dev/skills/bruchris/canvas-lms-mcp/canvas-gradebook-audit"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-gradebook-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/bruchris/canvas-lms-mcp/canvas-gradebook-audit"><img src="https://agentmods.dev/badge/skills/bruchris/canvas-lms-mcp/canvas-gradebook-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 | $0.00089 | $0.00828 |
| Opus 5 | $0.00044 | $0.00414 |
| Sonnet 5 | $0.00018 | $0.00166 |
| Haiku 4.5 | $0.00009 | $0.00083 |
Grade A, and why
canvas-gradebook-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 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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Canvas Gradebook Audit
Inspect the full audit trail of grade changes in a Canvas course. Useful for grade integrity checks, accreditation reviews, and catching accidental bulk edits.
Prerequisites
- Canvas MCP server must be running and connected.
- You must have instructor or admin role — grade history is restricted to privileged roles.
- Canvas must have gradebook history enabled on the instance (most institutions do).
Steps
1. Identify the Target Course
Ask the user which course to audit. Accept a course name, code, or Canvas ID.
If unclear, call list_courses to let them select.
2. Choose Audit Scope
Ask the user one of:
- Date range: "Audit grade changes between [start date] and [end date]"
- Assignment focus: "Show all grade edits for a specific assignment"
- Student focus: "Show all grade edits for a specific student"
Default to the past 30 days if no range is given.
3. Retrieve History Days
Call list_gradebook_history_days with the course ID. This returns a list of calendar days that had grade activity, with a summary count per day.
Filter to the user's requested date range.
4. Drill Into Each Day
For each day with activity, call get_gradebook_history_day with the course ID and the date string. This returns the graders who made changes and the assignments they touched.
Build a running summary:
- Grader name
- Number of submissions edited
- Assignments affected
5. Inspect Individual Edits (When Requested)
If the user wants to see the specific before/after values for a submission, call list_gradebook_history_submissions with the course ID, grader ID, assignment ID, and date. This returns per-student grade change records with old score, new score, and timestamp.
For a full chronological feed without filtering by grader, use get_gradebook_history_feed with the course ID (and optionally assignment ID or student ID).
6. Present the Audit Report
Gradebook Audit — [Course Name]
Period: [start date] → [end date]
SUMMARY
Total days with grade activity: 7
Total grade edits: 143
Graders active: 3
BREAKDOWN BY GRADER
• Prof. Martinez — 98 edits across 4 assignments (Apr 10–18)
• TA Chen — 42 edits across 2 assignments (Apr 12–14)
• System (auto-grade) — 3 edits (Apr 20)
NOTABLE CHANGES
• Assignment "Midterm Essay" — 12 students had scores changed on Apr 14
Old avg: 71.2 → New avg: 78.4 (grader: TA Chen)
• Student "Alex Doe" — grade changed 3 times on Apr 18 (possible error)
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 · 85 lines · 89 tokens per session scan A e0ec5eb42d53
canvas-gradebook-audit is a skill published in the GitHub repository bruchris/canvas-lms-mcp (5 stars, last pushed yesterday), licensed MIT. It adds 89 tokens to every session and 828 once invoked, about $0.0004 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
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…