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 git-asmt-pagegit 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/git-asmt-page)<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-page"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-page/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/git-asmt-page"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-page.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 | $0.00145 | $0.01357 |
| Opus 5 | $0.00072 | $0.00678 |
| Sonnet 5 | $0.00029 | $0.00271 |
| Haiku 4.5 | $0.00015 | $0.00136 |
Grade A, and why
git-asmt-page scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
git-asmt-page — Canvas page for a git assignment (L1 child)
The Canvas half of git-asmt. It does not build the repo (that's git-asmt-repo). It builds the
page and its parts, in the standard format the global builder produces. You never hand-write
the page HTML or the gDoc — you fill the asmt dict and call git_page; it renders the instruction
gDoc AND the page from the same dict (so they always agree) and uploads it (unpublished).
import sys
sys.path.insert(0, "$CANVAS_LMS_ROOT/.claude/skills/assignment-page-builder")
from git_page import git_page
out = git_page(course_slug, asmt, points=N, push=True, due_at="…Z")
The parts this page must carry (the "common elements")
Every git-assignment page, built from the asmt dict:
- Instruction — what to make:
gist(1 line) +spec(what each case does) +algorithm. - Function contract — the core prototype, parameters, return (
io: Parameter / Return lines). For a stdin program instead, the I/O is the stdin→stdout contract (no prototype). - Examples —
call → outputpairs (verbatim from the spec/slides; RUN it, paste the real result). - Restrictions — yellow box (what NOT to do; mirrors what the tests enforce).
- Elaboration — navy box: exactly what the student must WRITE (graded) — algorithm, edge correctness, errors→fixes with commit links.
- Test-items table — per grader (Compile/Run/T1..Tn) with max points and what it checks, taken from the ACTUAL test file (never invented).
- Per-item points / Rubric — the
Item | Points | Criteriatable summing topoints_possible(autograder / elaboration / commit / repo-link split — GRADING.md).points=N→ git_page distributes byrubric_weights; never hardcode per-item numbers. - Request link —
…/classroom/issues/new?template=<request_form>&assignment=<CODE>(git_page builds it fromrequest_id=CODE; requires the CODE registered bygit-asmt-repofirst). ⛔ ONE VALUE, FOUR PLACES.request_id=code= the assignment slot in the student repo name = the org-hubconfig.jsonkey:<course>-<term>-A612-<student-login>·<COURSE>A612Starter· key"A612".request_idexists only for the ~1% assignment whose request key genuinely differs — passing a different value is a DECLARATION, not a default, andgit_pagenow STOPS on a silent divergence. Why: on 2026-08-04 all 14 CSCI-19A chapter-5 pages shippedassignment=5-6-style TITLES while the register heldA56, and nothing noticed for a whole chapter — the student request form is a dropdown generated fromconfig.json, so students picked the right entry and the broken pre-fill stayed invisible. - Full guide — the embedded instruction gDoc (git_page makes it in
pages_folder).
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 · 73 lines · 145 tokens per session scan A cd2bfd57089f
git-asmt-page is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 145 tokens to every session and 1,357 once invoked, about $0.0007 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
magpie-newcomer-issue-explainer
Given an open good-first-issue on the configured repo, explain it in beginner terms and sketch a concrete approach: which files to read first, what "done" looks like, and where to ask follow-up questions — without writing any code or fix. First runs an issue assessment to confirm the issue is open, non-security, and…
lesson-close
A workflow for finishing the day's lesson file, recording its status and duration, then saving it to the personal-guide GitHub repository.
github-contributor
Find suitable open-source contribution opportunities and prepare focused GitHub pull requests with project-specific validation and review context.
stage-and-commit
Stage changed files and create a commit following the repo's translation, formatting, and git workflow rules. Use when the user asks to stage, commit, or both.
textbook-init
A setup assistant for starting a textbook project or a workspace for several textbooks. It asks about the project, creates the directory structure, and can add version control and a README.
conflict-resolver
Résolution de conflits entre agents ou sous-agents quand les résultats sont contradictoires, avec workflow de détection, arbitrage, merge et feedback loop. Se déclenche avec "conflit agent", "agent conflict", "résultats contradictoires", "agent disagreement", "contradiction agents", "arbitrage agent", "résoudre…