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 Jartan-LLC/grimoire --skill github-conventionsgit clone --depth 1 https://github.com/Jartan-LLC/grimoireWrote 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/jartan-llc/grimoire/github-conventions)<a href="https://agentmods.dev/skills/jartan-llc/grimoire/github-conventions"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/github-conventions/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/skills/jartan-llc/grimoire/github-conventions"><img src="https://agentmods.dev/badge/skills/jartan-llc/grimoire/github-conventions.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 | $0.00028 | $0.00714 |
| Opus 5.5 | $0.00011 | $0.00286 |
| Sonnet 5.5 | $0.00006 | $0.00143 |
| Haiku 4.5 | $0.00003 | $0.00071 |
Grade A, and why
github-conventions 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 2d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitHub Conventions
CRITICAL: #<number> auto-links to issues/PRs on GitHub. Use 1./2./3. for numbered lists and "Finding 1:"/"Item 1:" for labeled items -- never #1, #2, #3 as markers.
Where the project's own rules say otherwise, follow them.
Authentication
Never reconfigure auth transport to unblock a command. Don't switch the remote between SSH and HTTPS, add a credential helper, or push to an explicit URL. A missing key or token scope is a missing credential, not a transport problem -- only the user can supply it, and working around it changes config they never asked you to touch, often globally. Stop and ask.
Branches
Feature branches: feature/<description> or feature/issue-<number>
Always check if a branch already exists for an issue before creating a new one.
For sub-issues of a larger feature, branch from the parent feature branch rather than main. Sub-issue work merges back into the parent feature branch, which eventually merges to main.
Commits
Follow the project's commit convention, as CONTRIBUTING, a commitlint config or the agent instructions state it, or as recent single-commit subjects on the default branch show it. Where none does, use Conventional Commits: <type>(<scope>): <description>, with a type from commitlint's config-conventional (build, chore, ci, docs, feat, fix, perf, refactor, revert, style, test); the scope is optional.
Mark a change that breaks something for the project's consumers the way the convention and the project's release tool read it: ! before the colon, a BREAKING CHANGE: footer, or both; where you cannot tell, both. A one-time action only contributors owe (rebuild the dev container) takes no breaking mark.
While a commit is not yet pushed, fold a further fix to the same change into it (git commit --amend for the last commit) instead of adding a commit. Never rewrite a pushed commit.
For what a commit message, a PR title and a PR description say, and which of them lands on the default branch, load gitwise:commit-pr-writing.
What ships with it
2 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.
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.
- 2d ago Changed · +5 lines a63ecf10866d
- 1mo ago First seen · 54 lines · 28 tokens per session scan A d0d48312f8e3
github-conventions is a skill published in the GitHub repository Jartan-LLC/grimoire (2 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 714 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 2026-08-31.
Other skills, from other repositories
git-commit
Use when asked to commit, save, or persist changes to Git. Handles atomic commits, branch safety, Conventional Commits format, and project style matching. Do NOT use for pushing, creating PRs, or branch management beyond safety checks.
commit
Draft a git commit message documenting what changed and why, with the findings that drove it, for review before committing.
orient-commit
Draft a git commit message documenting what changed and why, with the findings that drove it, for review before committing.
conventional-commits
Create Git commits using Conventional Commits with a scoped Chinese subject and a concise bullet-list body. Use when Codex is asked to commit changes, prepare a commit message, amend a commit message, or review whether a proposed commit follows the required format.
writing-commit-messages
Write a commit message that describes the focus of the change, not its supporting work. Use when committing.
git-hygiene
Execute explicitly requested version-control mutations safely, including staging, commits, branches, merges, rebases, conflict resolution, undo operations, and pull-request preparation. Always use before force push, reset, clean, history rewrite, or deletion. Do not trigger for read-only status, diff, log, blame, or…