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 nikeyes/stepwise-dev --skill ship-prgit clone --depth 1 https://github.com/nikeyes/stepwise-devWrote 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/nikeyes/stepwise-dev/ship-pr)<a href="https://agentmods.dev/skills/nikeyes/stepwise-dev/ship-pr"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/ship-pr/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/nikeyes/stepwise-dev/ship-pr"><img src="https://agentmods.dev/badge/skills/nikeyes/stepwise-dev/ship-pr.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 | $0.00053 | $0.01135 |
| Opus 5.5 | $0.00021 | $0.00454 |
| Sonnet 5.5 | $0.00011 | $0.00227 |
| Haiku 4.5 | $0.00005 | $0.00113 |
Grade A, and why
ship-pr 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 8d 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship PR
Take the work in this repository to a pull request that is ready to merge: commit it, push it, open the PR, wait for its checks, fix what fails and answer the review comments.
Nobody will answer questions while you run. Do not ask for confirmation at any step: the report you write at the end is the user's control point. Never merge the PR and never force-push.
Your Role: Orchestrator
You coordinate; the delegated skills do the work and own their rules. Invoke each one with the Skill tool:
/stepwise-git:commitcreates the commits/stepwise-git:open-prpushes, opens the PR and waits for the checks/stepwise-git:review-pr-commentsdecides on the comments, implements, pushes and replies/stepwise-core:tddfixes behavior test-first, when it is available
If a delegated skill fails, stop and report what happened. Do not work around it by doing its job yourself.
Getting Started
- Plan: if a plan file is given, pass it to
tddand toreview-pr-commentsas context. Do not look for one yourself. - Nothing to ship: if the working tree is clean, the branch has no commits ahead of the default branch and it has no open PR, say so and stop.
- Branch first: if you are on the default branch and there are changes to commit, create
type/short-descriptionwithgit switch -cbefore committing. - Commit: if there are uncommitted changes, invoke
/stepwise-git:commit.
Then run the round cycle. Keep a count of fix rounds, starting at 0.
Round Cycle
Step 1 — Push and wait
Invoke /stepwise-git:open-pr. It pushes whatever is not on the remote yet, so the fixes of the previous round are verified here.
Stop with timeout if checks are still pending when it returns.
Stop with round limit if the fix-round count is 3. The comments that arrived after the last push have not been processed: say so in the report.
Step 2 — Fix the failed checks
Skip this step if no check failed.
Stop with no progress if a check fails with the same error as in the previous round.
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.
- 8d ago First seen · 99 lines · 53 tokens per session scan A a4fee926232b
ship-pr is a skill published in the GitHub repository nikeyes/stepwise-dev (24 stars, last pushed 6d ago), licensed Apache-2.0. It adds 53 tokens to every session and 1,135 once invoked, about $0.0002 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 2026-10-11.
Other skills, from other repositories
create-pr
Creates a GitHub PR with a Linear-ticket-prefixed title and a decision-led, narrative description for Prisma 8. Use when the user wants to create a pull request, open a PR, or submit changes for review.
git-commit
Generate well-formatted git commit messages following conventional commit standards.
repo-sync
Manage automatic Git syncing on macOS with repo-sync. Use only when the user explicitly invokes /repo-sync.
mcore-split-pr
Split a PR into multiple PRs to reduce the number of required CODEOWNERS reviewer groups.
contributing
How to contribute to evlog, covering commit and PR conventions, changesets, the Definition of Done, testing rules, and the authored skills that walk through building a new adapter, enricher, framework integration, or map rule. Load this for any question about contributing, opening a PR, or adding something to the…
git-commit-writer
Trigger when the user asks to write a commit message, generate a commit from staged changes, review a diff before committing, or says "/commit". Reads git diff --staged and produces an opinionated, convention-matching commit message.