A11y LLM Evaluation Harness and Dataset is a test suite for measuring how well language models generate accessible HTML. It runs agent-generated pages in a browser and evaluates them with automated accessibility checks.
Borrowing it
Nothing to install: this file belongs to microsoft/a11y-llm-eval. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/microsoft/a11y-llm-eval/main/.github/agents/git-commit.agent.mdgit clone --depth 1 https://github.com/microsoft/a11y-llm-evalWrote 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/agents/microsoft/a11y-llm-eval/git-commit)<a href="https://agentmods.dev/agents/microsoft/a11y-llm-eval/git-commit"><img src="https://agentmods.dev/badge/agents/microsoft/a11y-llm-eval/git-commit/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/agents/microsoft/a11y-llm-eval/git-commit"><img src="https://agentmods.dev/badge/agents/microsoft/a11y-llm-eval/git-commit.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 | $0.00034 | $0.00238 |
| Opus 5.5 | $0.00014 | $0.00095 |
| Sonnet 5.5 | $0.00007 | $0.00048 |
| Haiku 4.5 | $0.00003 | $0.00024 |
Grade A, and why
Git Commit 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 2mo 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.
What it actually says
You create safe, reviewable git commits for this repository.
Rules
- Only commit when the user explicitly asks for a commit or asks to finalize changes.
- Inspect
git statusand the relevant diffs before staging anything. - Stage only files that belong to the requested change.
- If the worktree contains unrelated edits, ask before including them.
- Use non-interactive git commands only.
- Use commit subjects that start with
feat:,fix:, orchore:. - Do not amend commits, rebase, or push unless the user explicitly asks.
Workflow
- Review the changed files and diffs.
- Confirm the intended scope of the commit.
- Stage only the relevant files with explicit paths.
- Create a commit message using the required prefix.
- Create the commit.
- Report the commit message and the files included.
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.
- 2mo ago First seen · 27 lines · 34 tokens per session scan A e6a8cb88566a
Git Commit is an agent published in the GitHub repository microsoft/a11y-llm-eval (62 stars, last pushed 5mo ago), licensed MIT. It adds 34 tokens to every session and 238 once invoked, about $0.0001 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 agents, from other repositories
secrets-detector
Detects committed secrets and credentials so they can be removed and rotated. Use to scan a repo defensively before making it public or as a pre-commit safeguard.
plastic-node-work
Dispatched for a work node by Plastic's node-graph runner. Given the node input path the dispatch line names, make the node's code changes inside the node worktree, commit them there, and reply with the YAML return the dispatch line names. Never spawned outside a runner dispatch.
pr-ghostwriter
Kod değişikliklerinden PR açıklaması, commit mesajı ve changelog üretir. Gerçek diff'i okuyarak değişikliğin ne, neden ve nasıl olduğunu açıklar. Kullanıcı PR açmak, commit mesajı yazmak veya release notu hazırlamak istediğinde kullanılır. Jenerik açıklama üretmez — her zaman gerçek değişikliğe özgü yazar.
commit
Runs the auto-commit skill.
git-specialist
Git workflow specialist. Use for any git work — staging, conventional commits, branch creation, pushing with upstream tracking, PR creation via gh (GitHub) or az (Azure DevOps). Auto-detects host from origin. Enforces strict commit and branch naming.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.