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 xonovex/platform --skill git-guidegit clone --depth 1 https://github.com/xonovex/platformWrote 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/xonovex/platform/git-guide)<a href="https://agentmods.dev/skills/xonovex/platform/git-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/git-guide/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/xonovex/platform/git-guide"><img src="https://agentmods.dev/badge/skills/xonovex/platform/git-guide.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 | $0.00069 | $0.01085 |
| Opus 5.5 | $0.00028 | $0.00434 |
| Sonnet 5.5 | $0.00014 | $0.00217 |
| Haiku 4.5 | $0.00007 | $0.00109 |
Grade A, and why
git-guide 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.
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git Guidelines
Create conventional commits, resolve conflicts, and manage worktrees with explicit validation and publication steps.
Core Principles
- Conventional Commits - Use type prefixes (feat, fix, chore, docs, refactor, test, ci), see references/commit.md
- Auto-Generate Messages - Analyze changed files and context, see references/commit.md
- Isolated Development - Use worktrees for feature branches, see references/worktree-create.md
- Validate Before Merge - Run typecheck/lint/build/test, see references/worktree-validate.md
- Publish and Rebase - Push a branch upstream and rebase onto the base before opening a PR / MR, see references/push.md
- Explicit Effects - Worktree create, merge, and cleanup default to preview and mutate only for an explicit apply
Commit Operations
- Auto-commit - Analyze changes, infer type, generate message, optional push, see references/commit.md
Branch Operations
- Push + rebase-onto-base - Publish a branch upstream and keep its PR / MR diff just this change; the host skill (
github-guide/gitlab-guide) drives the PR itself, see references/push.md
Conflict Resolution
- Detect and classify - Find conflicts, suggest strategy (ours/theirs/merge), see references/merge-resolve.md
- Validate - Run typecheck/lint after resolution before staging, see references/merge-resolve.md
Worktree Operations
- Create - Preview or apply creation of a
<worktree>-feature-<name>directory and branch, see references/worktree-create.md - Validate - Pre-merge validation checkpoint, see references/worktree-validate.md
- Merge - Preview or apply integration into the source branch without cleanup, see references/worktree-merge.md
- Cleanup - Preview or apply removal of exact stale or merged targets, see references/worktree-cleanup.md
- Abandon - Inspect and document a stopped feature without mutation, see references/worktree-abandon.md
What ships with it
12 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.
- eval-queries.json 4.5 KB
- evals.json 3.2 KB
- moon.yml 166 B
- references/commit.md 1.9 KB
- references/merge-resolve.md 709 B
- references/push.md 1.0 KB
- references/worktree-abandon.md 1.0 KB
- references/worktree-cleanup.md 1.5 KB
- references/worktree-create.md 2.0 KB
- references/worktree-merge.md 2.1 KB
- references/worktree-validate.md 617 B
- SOURCES.md 1.0 KB
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 Changed · +2 lines bb080bb1e0e0
- 1mo ago First seen · 63 lines · 69 tokens per session scan A c98a231fffd4
git-guide is a skill published in the GitHub repository xonovex/platform (6 stars, last pushed 4d ago), licensed MIT. It adds 69 tokens to every session and 1,085 once invoked, about $0.0003 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 2026-09-08.
Other skills, from other repositories
cw-land
Use when turning verified Codewhale work into commits, branches, or a merge: choosing direct-main vs. worktree vs. integration branch, preserving contributor credit, and honoring the gate artifact before merging.
atmos-git
Atmos Git and GitOps: git.repositories, clone/pull/status/diff/commit/push/clean, local Git hook shims and hook env vars, signed commits, managed workdirs, fork-PR trust gate (clone gate and posting gate), and auth via identities or github/sts.
setup-caliber
Sets up Caliber for automatic AI agent context sync. Installs pre-commit hooks so CLAUDE.md, Cursor rules, and Copilot instructions update automatically on every commit. Use when Caliber hooks are not yet installed or when the user asks about keeping agent configs in sync.
conventional-commit
Conventional Commit - Generate Conventional Commits 1.0.0 compliant messages. MANDATORY for all git commits. Invoke when user says 'commit', 'commit this', or asks to commit code.
blueprint
Generates a step-by-step construction plan from a one-line objective, where each step is self-contained and executable by a fresh agent in a new session.
contributing
Codex adapter for the opencode-swarm contribution checklist. Use when preparing user-visible changes, release note fragments, local validation, branch hygiene, PR checklist items, or contribution-policy compliance before publishing work.