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 aethrox/doctrine --skill repo-shipgit clone --depth 1 https://github.com/aethrox/doctrineWrote 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/aethrox/doctrine/repo-ship)<a href="https://agentmods.dev/skills/aethrox/doctrine/repo-ship"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/repo-ship/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/aethrox/doctrine/repo-ship"><img src="https://agentmods.dev/badge/skills/aethrox/doctrine/repo-ship.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 | $0.00068 | $0.00881 |
| Opus 5 | $0.00034 | $0.00441 |
| Sonnet 5 | $0.00014 | $0.00176 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
repo-ship 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 10d 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repo Ship
A commit history and a repository's first impression are both easy to get right at the moment they are made and expensive to fix afterward. This skill's defining constraint, extending Conventional Commits from classifying already-made commits into shaping how they get made in the first place: split by intent as work happens, not by file count after the fact, and treat a new repository's metadata as part of creating it, not a task for later. Write generated commit messages and repository metadata without em dashes, using a comma, colon, period, or a reworded sentence instead.
This is a different job from release-versioning, which classifies already-made commits into a version bump and changelog entry for a release that is shipping now. This skill governs the commits themselves while work is in progress, and a repository's first creation; release-versioning takes over once code already exists and a release is being cut.
Path A: Commit by intent for existing repository work
Use this path when existing work is about to be committed or pushed.
Phase A1: Split commits by intent, not by file count
A reader running git log --oneline should be able to tell what happened without opening a diff. One logical change per commit: a bug fix, a rename, and a new feature landing in the same commit is the pattern to avoid. If the working tree already mixes several intents, stage explicit paths per commit rather than staging everything at once. Formatting-only churn gets its own commit so it does not bury a real change inside it. Decide commit boundaries before editing when practical, especially when several intents will touch the same file. Use Conventional Commit types such as fix and feat, including a breaking-change marker where applicable, so release-versioning can later derive the SemVer bump from the history.
Phase A2: Verify the commits before reporting done
Inspect the actual commit log, working tree status, and upstream tracking relationship. If a push failed or a commit was amended along the way, report that plainly rather than reporting success by assumption.
What ships with it
1 file 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.
- 10d ago First seen · 56 lines · 68 tokens per session scan A 29d14ffff715
repo-ship is a skill published in the GitHub repository aethrox/doctrine (18 stars, last pushed 29d ago), licensed MIT. It adds 68 tokens to every session and 881 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
ce-commit
Create a git commit with a clear, value-communicating message. Use when the user asks to commit/save staged or unstaged changes with a repo-appropriate message.
ce-commit-push-pr
Commit, push, and open a PR. Use when asked to ship/open a PR, or for PR-description-only flows like writing, rewriting, or describing a PR body.
memorix-git-memory
Use when the task depends on commit history, what changed, when a fix shipped, or linking engineering evidence to reasoning memory.
repository-manager-bulk-git-operations
Bulk, parallel git operations across a whole workspace of repositories via the repository-manager MCP server — clone, pull, push, add, commit, pre-commit, phased push, and enumerate every repo across a GitLab instance / GitHub org into an ingest manifest (which also natively ingests them into the knowledge graph as…
source-command-improve
Run ONE iteration of the continuous-improvement loop — pick the highest-value backlog item, implement it, verify end-to-end, commit.
git-workflow
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, atomic commits, worktrees, change summaries, and disciplined version control for AI agents and developer teams.