grade-git-program

grade-git-program is a skill for Claude Code, Codex from Canvas-LMS-MCP/canvas-teacher-mcp. It costs 118 tokens per session (1,698 once invoked), scanned A, original, MIT.

A grading sub-step for Git programming assignments and Git programming questions in quizzes. It is used by a larger grading process and checks the submitted code against the relevant course rules.

In plain words
What is it for?
Use it when the grading system needs to assess a Git coding submission, with stricter checks for quiz questions than for homework.
Why use it?
It applies the rules for Git-based coding work in one place instead of requiring a separate grading approach for each assignment or quiz.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md.

Good fit Use it when the grading system needs to assess a Git coding submission, with stricter checks for quiz questions than for homework.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program
Install

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.

Any agent
npx skills add Canvas-LMS-MCP/canvas-teacher-mcp --skill grade-git-program
Clone the repo
git clone --depth 1 https://github.com/Canvas-LMS-MCP/canvas-teacher-mcp

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for grade-git-program

README.md
[![agentmods](https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program/github.svg)](https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program)
Your own site
<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program/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.

agentmods 80×15 button for grade-git-program

Your own site · 80×15
<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/grade-git-program.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 118 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,698 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00118 $0.01698
Opus 5 $0.00059 $0.00849
Sonnet 5 $0.00024 $0.00340
Haiku 4.5 $0.00012 $0.00170

Measured 9d ago against content hash 13fcc77fa803, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

grade-git-program 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 9d 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.

src/canvas_teacher_mcp/_data/skills/grade-git-program/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

grade-git-program — grade a git coding assignment / quiz question (SUB-SKILL of grade)

Type-specific plug-in for grade, like grade-nb. When a submission is a git coding item (a git-homework assignment OR a git-program quiz question), grade dispatches HERE, then returns to the general flow (report → self-challenge → POST). ONE skill covers homework + quiz (they are ~95% identical): the only difference is STRICTNESS — a quiz question is graded at the strict end (forbidden-function source check, exact-arrangement tests, a non-algorithm solution below half); a homework is looser. The weights come from GRADING.md, or from the course's Grading override: document when its CLAUDE.md declares one.

STATUS: PARTIAL (first grading = M1QP1, 2026-07-08). Autograder(50) + commit-server-time authenticity(§4F.4) are BUILT & wired through the engine; elaboration(30) is judged by Stage B on the instructions rubric. Remaining stubs: quiz-question forbidden-function source-check gate + per-question posting path (TODO below). Do NOT hand-roll grading — it RUNS THROUGH THE ENGINE (see below).

Runs through the engine (never hand-roll)

  • grade_engine.core.grade(config, code)graders/gh already grades GitHub assignments (autograder score via github_access.list_runs + parse_total_points_from_log_zip; commit-late). This sub-skill is the METHOD, not a standalone driver — same rule as grade-nb.
  • Policy home: CourseGlobalWorkflow/GRADING.md Part B (GitHub assignments), plus the course's Grading override: document when its CLAUDE.md declares one (GRADING.md Q4). Read whichever is in force; this file only adds the git-program-specific method.

Rubric (the in-force weights — see the policy home above)

Item Weight Source
Repo link submitted 5% submission
Autograder result (score/100 × this weight) 50% engine gh (Layer 1)
Elaboration (algorithm + all-inputs correctness + errors/lessons) 30% AI Stage B
Commit process (timing + count, genuine progression) 15% AI Stage B (server-time authenticity)

Read the full file on GitHub · 88 lines

Changes

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.

  1. 9d ago First seen · 88 lines · 118 tokens per session scan A 13fcc77fa803

Subscribe to this mod's changes

grade-git-program is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 25d ago), licensed MIT. It adds 118 tokens to every session and 1,698 once invoked, about $0.0006 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.

Related

Other skills, from other repositories

hr-onboarding

A new-hire onboarding plan as a single page — first week schedule, buddy + manager intro, learning track, equipment checklist, and "you're set when…" outcomes. Use when the brief mentions "onboarding", "new hire", "first week plan", or "入职".

nexu-io/open-design · 62 tokens

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

miniapp

Build a tiny interactive HTML playground only when someone asks to see, play with, or step through a mechanism.

yc-software/qm · 25 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

A course or workshop slide template with persistent learning goals, teaching pages, multiple-choice self-tests, and a wrap-up.

nexu-io/html-anything · 25 tokens

master-yinguang

A reference-based assistant for questions about Yinguang and Pure Land Buddhism, a Buddhist tradition focused on faith, ethical living, and practice connected with rebirth in the Pure Land. It can answer in Yinguang’s historical teaching style.

xr843/Master-skill · 274 tokens