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.
npx skills add hashiiiii/rules-for-ai --skill hashiiiii-gitgit clone --depth 1 https://github.com/hashiiiii/rules-for-aiWrote 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/skills/hashiiiii/rules-for-ai/hashiiiii-git)<a href="https://agentmods.dev/skills/hashiiiii/rules-for-ai/hashiiiii-git"><img src="https://agentmods.dev/badge/skills/hashiiiii/rules-for-ai/hashiiiii-git.svg" alt="Measured on agentmods" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00020 | $0.00541 |
| Opus 5 | $0.00010 | $0.00270 |
| Sonnet 5 | $0.00004 | $0.00108 |
| Haiku 4.5 | $0.00002 | $0.00054 |
Grade A, and why
hashiiiii-git 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 7d 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
Git Conventions
Use the same type for the branch name and the commit subject. Select the type one time.
When to Use
- Before
git switch -corgit checkout -b - Before
git commit
This skill does not define branch strategy, squash policy, rebase policy, or release tags.
Branch
<type>/<short-english-kebab>
Use short English words in kebab-case. Do not use issue numbers, additional prefixes, personal names, or Japanese text.
Examples: feat/yaml-parser, fix/nested-override-diff, docs/cli-usage
Commit
Use this format on one line: <type>: <subject>
Write the subject in English and use the imperative form. Start with a lowercase word.
Do not add a final period. Use 50 characters or fewer.
Example: feat: add YAML parser for .prefab files
Types
| Type | Use |
|---|---|
feat |
Add a feature or capability. |
fix |
Correct a defect. |
docs |
Change documentation only. |
style |
Change formatting or whitespace without behavior changes. |
refactor |
Change code structure without behavior changes. |
perf |
Improve performance. |
test |
Add or correct tests. |
build |
Change the build system or dependencies. |
ci |
Change the CI files. |
chore |
Do maintenance, such as a .gitignore change. |
revert |
Revert an earlier commit. |
Select the closest type. Do not create a new type.
Example
git switch -c feat/yaml-parser
git commit -m "feat: add YAML parser for .prefab files"
Common Mistakes
| Mistake | Fix |
|---|---|
| Body or bullets below the subject | Use one line only. |
| Japanese subject | Use English and the imperative form. Start with a lowercase word. |
| Subject with more than 50 characters | Use 50 characters or fewer. |
Branch such as feature/…, bugfix/…, john/…, or Japanese text |
Use <type>/<english-kebab> with a type from the table. |
| New type | Use one of the 11 types in the table. |
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.
- 7d ago First seen · 69 lines · 20 tokens per session scan A 64e5c1b1a977
hashiiiii-git is a skill published in the GitHub repository hashiiiii/rules-for-ai (10 stars, last pushed yesterday), licensed MIT. It adds 20 tokens to every session and 541 once invoked, about $0.0001 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.
Other skills, from other repositories
gitops
Git operations wrapper: sync, stage, commit, push. Generates Conventional Commits messages with .scratch artifact references. Use when the user says gitops, commit, push, sync code, or needs version control operations.
commit
Skill "commit" from clacky-ai/openclacky, covering smart commit skill, critical requirement: single-line commits only, core philosophy, usage and process steps.
devops-pipeline
Configure pre-commit hooks and lean GitHub Actions for shift-left quality assurance. Use when adding or auditing CI/CD to maximize local test coverage and minimize CI cost. Skip for Terraform/K8s, deployment pipelines, or non-GitHub CI providers.
auto-push
Generate a commit message, stage all changes, and push to remote after scanning for secrets, large files, and protected-branch risks. Skip for opening PRs, code review, or cutting releases/tags.
azure-repos
Expert knowledge for Azure Repos development including troubleshooting, best practices, decision making, architecture & design patterns, limits & quotas, security, configuration, and integrations & coding patterns. Use when managing Git/TFVC repos, branch/PR policies, CLI/IDE integrations, CodeQL/scanning, or…
cf-commit
Smart conventional commit with diff analysis. Triggers: "commit this", "commit my changes", "save my work", "create a commit", "git commit", "stage and commit".