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/RalfHuesing/ComputeToAiWrote 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/rules/ralfhuesing/computetoai/git-workflow)<a href="https://agentmods.dev/rules/ralfhuesing/computetoai/git-workflow"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/git-workflow/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/rules/ralfhuesing/computetoai/git-workflow"><img src="https://agentmods.dev/badge/rules/ralfhuesing/computetoai/git-workflow.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 | $0.00579 | $0.00579 |
| Opus 5.5 | $0.00232 | $0.00232 |
| Sonnet 5.5 | $0.00116 | $0.00116 |
| Haiku 4.5 | $0.00058 | $0.00058 |
Grade A, and why
git-workflow 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Vollagentische Entwicklung
Dieses Repo wird bewusst vollagentisch entwickelt, inklusive eigenständiger Commits durch den Agenten – anders als in klassischen Setups ist hier keine explizite Freigabe pro Commit durch den Nutzer nötig. Das gilt für alle Agenten, die an diesem Repo arbeiten (Claude Code, ggf. weitere), nicht nur für einen bestimmten.
Push auf ein Remote (git push) sowie destruktive Git-Operationen (reset --hard, push --force, Branches löschen, History umschreiben) bleiben davon ausgenommen und brauchen weiterhin ausdrückliche Nutzerfreigabe.
Wann committen
Ein Commit erfolgt pro abgeschlossener Teilaufgabe – einer in sich sinnvollen, kleinen, nachvollziehbaren Einheit. Beispiele: eine Doc-Änderung, eine neue/geänderte Funktion inklusive ihrer Tests, eine abgeschlossene Roadmap-Task. Nicht: ein einzelner Dateispeichervorgang (zu klein) und nicht ein ganzer Session-/Auftrags-Umfang in einem Commit (zu grob, schlecht nachvollziehbar/revertierbar).
- Änderungen an
src/werden nur committet, wenn die lauttesting.mdcvorgeschriebenen Tests vorhanden und grün sind. - Direkt auf
maincommitten ist der Standard-Workflow in dieser frühen Konzept-/Prototypenphase (Solo-Projekt, kein PR-Overhead). Feature-Branches sind kein Muss; sollte das Projekt später mehrere parallel/unbeaufsichtigt laufende Agenten bekommen, wird diese Regel überprüft.
Commit-Messages: Conventional Commits
Format: <type>(<scope>): <description>, englisch, im Imperativ, ohne Satzpunkt am Ende.
| Type | Wofür |
|---|---|
docs |
Änderungen an Docs/, README.md, CLAUDE.md, .agents/rules/ |
feat |
Neue Funktionalität in src/ |
fix |
Bugfix in src/ |
refactor |
Code-Umbau ohne Verhaltensänderung |
test |
Nur Tests hinzugefügt/geändert |
chore |
Tooling, Dependencies, Repo-Housekeeping |
build |
Build-/Packaging-Konfiguration (pyproject.toml u. Ä.) |
scope ist optional, wenn er Klarheit schafft (z. B. feat(engine): add Store balance rollup, docs(finance): clarify cash-bucket priority). Bei Bedarf ein kurzer Body für das Warum, nicht das Was (das zeigt der Diff).
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 · 34 lines · 579 tokens per session scan A 41f8ba9659ff
git-workflow is a cursor rule published in the GitHub repository RalfHuesing/ComputeToAi (0 stars, last pushed 2mo ago), licensed MIT. It adds 579 tokens to every session, about $0.0023 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 cursor rules, from other repositories
conventional-commits
Enforce Conventional Commits format for all commit messages.
development-workflow
Cursor rule "development-workflow" from floriscornel/todo-mcp, covering development workflow for todo mcp, testing & quality assurance, commit structure, branch & pr workflow and publication & releases.
windsurfrules
Pare wraps CLI tools in MCP servers returning structured JSON. Always prefer Pare MCP tools over raw CLI.
git-commits
Apply when generating git commit messages, performing commits, pushing to remote, or suggesting commit-related changes. Enforces Conventional Commits format and pre-push CI verification.
50-pr-and-git
Use when committing, opening or updating a pull request, writing a PR description, or preparing a release.
conventional-commits
Conventional Commits rules and examples for this repo.