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 ASMN-96/ai-agents-skills-toolkit --skill shipgit clone --depth 1 https://github.com/ASMN-96/ai-agents-skills-toolkitWrote 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/asmn-96/ai-agents-skills-toolkit/ship)<a href="https://agentmods.dev/skills/asmn-96/ai-agents-skills-toolkit/ship"><img src="https://agentmods.dev/badge/skills/asmn-96/ai-agents-skills-toolkit/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/asmn-96/ai-agents-skills-toolkit/ship"><img src="https://agentmods.dev/badge/skills/asmn-96/ai-agents-skills-toolkit/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 | $0.00047 | $0.00777 |
| Opus 5.5 | $0.00019 | $0.00311 |
| Sonnet 5.5 | $0.00009 | $0.00155 |
| Haiku 4.5 | $0.00005 | $0.00078 |
Grade A, and why
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 1mo 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship route
Finish work that is already implemented: verify it, decide how to integrate it, and describe it honestly. This route never edits application code — it verifies, commits, and describes.
Paths below are relative to this skill's folder (in Claude Code: ${CLAUDE_SKILL_DIR}).
1. Verify before any completion claim
Read upstream/verification-before-completion/UPSTREAM.md and follow its Iron Law: no completion claim without fresh verification evidence run in this session. Before saying tests pass, a build succeeds, or a bug is fixed, identify the command that proves it, run the full command now, and read its actual output. A prior run, "should pass," or an agent's self-report is not evidence.
2. Decide how to integrate
Read upstream/finishing-a-development-branch/UPSTREAM.md and follow its flow: verify tests first (stop and report failures if they fail — do not proceed to the menu), detect whether this is a normal repo, a named-branch worktree, or a detached HEAD, confirm the base branch, then present the matching options menu and wait for the human's choice before merging, pushing, or discarding anything.
3. Write the artifacts
- Commit messages and PR descriptions: use
references/pr-description.md. The "How verified" section is mandatory and must name real command output, including anything skipped. - Release notes and rollback planning, especially for schema/migration/flag-sensitive changes: use
references/release-checks.md.
Precedence (overrides upstream text)
- The project's own scripts and CI define "verified," not this skill's judgment. If the project has a test/build/lint command, run that command — do not substitute a partial check.
- Upstream's discard-the-work path in
finishing-a-development-branchonly ever runs on an explicit, exact request from the human (the literal word "discard" per upstream's confirmation step). Never infer consent to discard, merge, push, or force-push from enthusiasm or vague agreement. - Remove only worktrees this session created; leave host-managed ones (for example
.claude/worktrees/) in place. - Never force-push, skip hooks, or push to the default/shared branch unless the human explicitly asks for that specific action in this conversation. If asked to force-push to main or skip a failing check to unblock a merge, refuse and propose the safe path instead (fix the failure, or push a new branch and open a PR).
- Code review of the diff itself belongs to the
reviewroute; security sign-off (auth, secrets, dependency, supply-chain risk) belongs to thesecureroute. This route may point to them but does not replace them. - Never claim a test, build, browser check, or scan passed unless its output is in this session. If something was not run, say so in the report instead of assuming it would pass.
What ships with it
6 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.
- 1mo ago First seen · 36 lines · 47 tokens per session scan A 57838b4c3185
ship is a skill published in the GitHub repository ASMN-96/ai-agents-skills-toolkit (5 stars, last pushed 27d ago), licensed MIT. It adds 47 tokens to every session and 777 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 2026-09-27.
Other skills, from other repositories
git-workflow
Git workflow patterns including branching strategies, commit conventions, merge vs rebase, conflict resolution, and collaborative development best practices for teams of all sizes.
writing-modpack-changelog
Use when cutting a modpack release. Creates /docs/release-changelog.md if absent; appends a new version section with grouped changes. Triggers - 'cut a release', 'release notes', 'changelog', 'v1.2.3 changes', 'what changed since last version'.
multi-repo-release
Prepares and validates GPT-RAG umbrella and multi-repository releases. Use whenever work involves release preparation, semantic versions, release branches, manifest or component pins, changelog release entries, tags, GitHub Release notes, or AI Landing Zone release alignment.
publish-npm-package
Configure or troubleshoot npm package publication with GitHub Actions and npm Trusted Publishing. Use this skill for JavaScript or TypeScript packages. Also use it for the npm package in a mixed-language repository. Do not use it for applications or repositories without an npm package. Do not use it for generic CI…
ship
Role: Release Engineer Inputs: plan.md, review-report.md (no [BLOCK] findings) Outputs: git commits, opened PR, trace link updates Audit actions: ship.started, ship.testsbootstrapped, ship.propened.
land-and-deploy
Role: Release Engineer Inputs: open PR (from /ship) Outputs: merged PR + deploy verification Audit actions: land-and-deploy.merged, land-and-deploy.deployed, land-and-deploy.verified.