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.
git clone --depth 1 https://github.com/mfmezger/ai_agent_dotfilesWrote 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/commands/mfmezger/ai_agent_dotfiles/github-pr)<a href="https://agentmods.dev/commands/mfmezger/ai_agent_dotfiles/github-pr"><img src="https://agentmods.dev/badge/commands/mfmezger/ai_agent_dotfiles/github-pr/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/commands/mfmezger/ai_agent_dotfiles/github-pr"><img src="https://agentmods.dev/badge/commands/mfmezger/ai_agent_dotfiles/github-pr.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 | $0.00062 | $0.01063 |
| Opus 5.5 | $0.00025 | $0.00425 |
| Sonnet 5.5 | $0.00012 | $0.00213 |
| Haiku 4.5 | $0.00006 | $0.00106 |
Grade A, and why
github-pr 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 1mo 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Workflow
This command guides the process of moving local changes to a GitHub Pull Request.
Prerequisites
gitmust be installed and configured.gh(GitHub CLI) must be installed and authenticated.
Commit Message Format
Use Conventional Commits with this required format:
<type>(<scope>): <summary>
typeREQUIRED. Common values:feat,fix,docs,refactor,chore,test,perf,ci,build,style.scopeREQUIRED. Short noun for the changed area (for example:config,api,ui,docs).summaryREQUIRED. Imperative, <= 72 chars, no trailing period.
Rules:
- Never add AI attribution anywhere in the GitHub workflow. Do not write
Generated by ...,Co-authored-by: Claude,Co-authored-by: Opus,Co-authored-by: Sonnet, or any other AI/model/agent attribution. - This ban applies to commit subjects, commit bodies, commit footers, PR titles, PR bodies, and PR comments. Do not add it even if a default template, tool, model habit, or previous workflow suggests it.
- Do not add sign-offs or breaking-change footers unless the user requests them.
Workflow Steps
Follow this order exactly: confirm branch state, stage, commit, push, then handle the PR.
-
Branch Check / Creation
- Check the current branch before doing anything else.
- If already on a suitable non-default working branch, stay on it.
- If on a default branch such as
mainormaster, create a feature branch first. - Identify the scope of changes (e.g.,
feat,fix,docs,chore). - Propose a branch name following the pattern
<type>/<kebab-case-description>. - Execute when a new branch is needed:
git checkout -b <branch-name>
-
Review & Stage Changes
- Review changes with
git statusandgit diff. - By default, stage only the files that belong to the current requested change.
- If the user provided file paths/globs, stage only those files.
- If there are ambiguous extra changed files, ask before staging/committing and leave them unstaged unless the user explicitly includes them.
- Stage the intended files with
git add .... - Optionally inspect recent subjects for local scope patterns:
git log -n 10 --pretty=format:%s.
- Review changes with
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.
- 1mo ago First seen · 89 lines · 0 tokens per session scan A 618aeaf16d46
github-pr is a command published in the GitHub repository mfmezger/ai_agent_dotfiles (7 stars, last pushed 3mo ago), licensed MIT. It adds 62 tokens to every session and 1,063 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
code-scrub
Audit merged pull requests over a user-specified number of days.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
mach12:gh-pr-read
Read a GitHub pull request's title, body, and all top-level PR conversation comments; optionally locate an HTML-marker comment.