What is git-asmt-repo?

A general workflow for building and testing GitHub coding-assignment repositories with an automated grader. It covers auditing instructions, testing that the assignment is faithful, proving a full score and shipping the starter repository.

Use it to audit an assignment, create its test harness, run the exact commands defined in classroom.yml, verify a 100/100 result and prepare the Starter repository. Language skills provide the compile, run and assertion details.

It separates the overall assignment process from language-specific details such as compiling, running and checking output. This makes the same workflow reusable across courses and programming languages.

git-asmt-repo — Skill for Claude Code and Codex by Canvas-LMS-MCP

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 git-asmt-repo

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo/github.svg)](https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo)

Your own site

<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo"><img src="https://agentmods.dev/badge/skills/canvas-lms-mcp/canvas-teacher-mcp/git-asmt-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 126 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 5,802 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.

Model	Per session	Once invoked
Fable 5.1	$0.00126	$0.05802
Opus 5	$0.00063	$0.02901
Sonnet 5	$0.00025	$0.01160
Haiku 4.5	$0.00013	$0.00580

Measured 12d ago against content hash 02a483639e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

git-asmt-repo 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.

The scan reads SKILL.md. This mod also ships 4 executable files (languages/cpp-stdout/template/data/run.sh, languages/cpp-stdout/template/main_test.py, languages/python-pytest/template/main_test.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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/git-asmt-repo/SKILL.md · 359 lines

How it starts

The opening of the file, as written. The whole thing — 359 lines — stays where its author put it; the contents beside it link to each section on GitHub.

git-asmt-repo — GLOBAL abstract (L1)

The language-agnostic core of "build + test a GitHub coding assignment for the org-hub." It owns the procedure and the gates; it never says g++, pytest, or Catch2. Those live in L2 language skills; the course id/org/prefix/curriculum live in the L3 course wrapper.

L1 (this)  git-asmt-repo/SKILL.md      ← WHAT: audit · fidelity · prove-100 · ship · gates
L2         git-asmt-repo/languages/    ← HOW in a language: compile/run/assert
              python-pytest.md · cpp-stdout.md · cpp-catch2.md
L3 (local) <course>/.claude/skills/…-git…   ← WHICH: org, prefix, language, chapter→model map (config)

The seams L1 leaves lower layers = four slots. Three are L2 (language): COMPILE, RUN, ASSERT(case). One is L3 (course + term): PROVISION — HOW the local dir → repo → Starter is created, which differs per course and changes per semester (see Part C). L1 calls all four abstractly; L2 fills compile/run/assert for the language, the L3 wrapper/config fills provision for the course.

The CORE RULE (inherited by every L2): classroom.yml IS the test spec — run its command: lines verbatim, in its order. Never assume the method or infer it from the files present. Step 0 of any test is always: open the repo's .github/workflows/classroom.yml and read its graders + order.

⛔ STEP 0b — DIFF THE REPO AGAINST ITS L2 TEMPLATE, EVERY BUILD. The harness files have ONE source, per language:

languages/<cpp-catch2|cpp-stdout|python-pytest|java-junit>/template/
        …/.github/workflows/classroom.yml   ← the true grader config
        + the harness files that model needs (tests, runner, Makefile, .gitignore, README)

An existing course repo is a COPY of some older template and drifts silently. Before building, shipping, or "fixing" anything, diff the repo's classroom.yml against its template and say out loud which graders differ. Never edit a repo's yml to correct it — change the TEMPLATE, then propagate (local dir → solution master → Starter, all three, per Part C). The CORE RULE above still governs how you RUN an already-released repo; this governs what a NEW one is built from. (2026-08-02: three repos each carried a retired -fsanitize=address grader; the template had dropped it long before, and no skill file said where the template lived.)

Read the full file on GitHub · 359 lines

Files

What ships with it

36 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

12d ago First seen · 359 lines · 126 tokens per session scan A 02a483639e5d

Subscribe to this mod's changes

git-asmt-repo is a skill published in the GitHub repository Canvas-LMS-MCP/canvas-teacher-mcp (1 stars, last pushed 27d ago), licensed MIT. It adds 126 tokens to every session and 5,802 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.

Testing

research-engineer

An uncompromising Academic Research Engineer. Operates with absolute scientific rigor, objective criticism, and zero flair. Focuses on theoretical correctness, formal verification, and optimal implementation across any required technology.

davila7/claude-code-templates · 43 tokens

tika-eval-compare

Compare extracts from two Tika builds over a corpus to detect regressions in content, encoding, exceptions, and embedded-document handling. Use for "compare before/after extracts", "eval this change against the corpus".

apache/tika · 50 tokens

neuron-evaluation-engineer

Create and run AI evaluations with datasets, assertions, and output drivers in Neuron AI. Use this skill whenever the user mentions evaluation, testing AI systems, creating evaluators, dataset-driven testing, assertion-based validation, or wants to measure AI system performance. Also trigger for tasks involving…

neuron-core/neuron-ai · 77 tokens

git-asmt-repo