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 Jerry0022/dotclaude --skill do-shipgit clone --depth 1 https://github.com/Jerry0022/dotclaudeWrote 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/jerry0022/dotclaude/do-ship)<a href="https://agentmods.dev/skills/jerry0022/dotclaude/do-ship"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-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/jerry0022/dotclaude/do-ship"><img src="https://agentmods.dev/badge/skills/jerry0022/dotclaude/do-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 | $0.00206 | $0.15609 |
| Opus 5.5 | $0.00082 | $0.06244 |
| Sonnet 5.5 | $0.00041 | $0.03122 |
| Haiku 4.5 | $0.00021 | $0.01561 |
Grade A, and why
do-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 11d 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 — 487 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ship
Ship completed work via PR using the dotclaude MCP server tools. Supports two modes: direct (branch → main) and intermediate (sub-branch → feature branch).
cwdis required on every MCP tool call. The ship MCP server runs in the plugin directory, not the target repo. Everyship_*tool call MUST includecwdset to this session's working directory, or it operates on the wrong repository.
Pipeline at a glance
The map of one run; each step's full rules are further down. Special cases live in deep-knowledge/ — each step names the moment to read its file (index at the end).
| Step | What | Call | Ends the run when |
|---|---|---|---|
| Pre-Steps 0, R, A–C | delegate, resume, lockout, session activity, sidebar title | autonomous-lockout.js check --ship |
activity pending (ask; BLOCK under lockout) |
| 0 / 0.5 | extensions, Codex detection, ship tool schemas | ToolSearch select:… |
server skipped → same steps via mcp-server/ship/cli.js; tools absent → deep-knowledge/manual-ship.md |
| 1 | preflight + rebase loop, purpose alignment, harden/polish passes | ship_preflight |
ready: false; ambiguous conflict |
| 2 | build + Codex gate | ship_build, codex-safe.sh |
build red; Codex judgment (ask; BLOCK under lockout) |
| 2.5 / 2.6 | deploy-parity build (background), docs-sync | deploy-parity.js |
parity failed |
| 3 | CHANGELOG + bump (final ship to main only) | ship_version_bump |
success: false; major (ask; BLOCK under lockout) |
| 4 | commit, PR, CI, merge, alpha tag | ship_release |
success: false without merged |
| 4a–4d | delivery hook, watcher, live surfaces, out-of-band deploy gate | — | never (card fields) |
| 5a–5c | keep-mode decision, cleanup | ship_cleanup |
ExitWorktree fails |
| 5d | promote (beta/stable named by the user) | ship_promote |
never (guard error → open item) |
| 5e, 6 | memory dream, promotion gap, hygiene, card — the last action | ship_hygiene, render_completion_card |
— |
What ships with it
37 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.
- deep-knowledge/branching.md 1.2 KB
- deep-knowledge/build-id.md 1.9 KB
- deep-knowledge/build-reuse.md 3.4 KB
- deep-knowledge/call-examples.md 1.7 KB
- deep-knowledge/cleanup.md 11 KB
- deep-knowledge/codex-gate.md 1.2 KB
- deep-knowledge/completion-card-payloads.md 9.1 KB
- deep-knowledge/composed-ships.md 1.9 KB
- deep-knowledge/data-flow.md 1.8 KB
- deep-knowledge/docs-sync.md 1.9 KB
- deep-knowledge/extensions.md 1.4 KB
- deep-knowledge/hierarchical-merge.md 1.8 KB
- deep-knowledge/manual-ship.md 4.0 KB
- deep-knowledge/memory-dream.md 1.0 KB
- deep-knowledge/offline-cli.md 1.2 KB
- deep-knowledge/post-merge-steps.md 8.6 KB
- deep-knowledge/post-merge-verify.md 7.6 KB
- deep-knowledge/pre-flight.md 4.2 KB
- deep-knowledge/preflight-rebase.md 4.9 KB
- deep-knowledge/purpose-alignment.md 12 KB
- deep-knowledge/quality-gates.md 3.1 KB
- deep-knowledge/release-flow.md 4.0 KB
- deep-knowledge/release-results.md 15 KB
- deep-knowledge/repo-modes.md 2.1 KB
- deep-knowledge/session-title.md 1.9 KB
- deep-knowledge/ship-passes.md 2.3 KB
- deep-knowledge/target-channel.md 933 B
- deep-knowledge/versioning.md 4.5 KB
- gate-contract.test.js 19 KB runs code
- modes/delegated.md 14 KB
- modes/promote.md 10 KB
- modes/resume.md 3.0 KB
- reference-graph.test.js 5.0 KB runs code
- reference.md 4.8 KB
- session-title.test.js 4.5 KB runs code
- ship-flow.test.js 12 KB runs code
- triggers.de.txt 61 B
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.
- 11d ago Changed 6884f58f3d74
- 15d ago Changed 50a30ac511a1
- 16d ago Changed · +293 lines · +156 tokens per session b55337d02813
- 28d ago Changed · +5 lines 3a640ea690e1
- 1mo ago Changed · +12 lines 13f1edd6f2c1
- 1mo ago First seen · 177 lines · 50 tokens per session scan A 9b8d93fcb882
do-ship is a skill published in the GitHub repository Jerry0022/dotclaude (6 stars, last pushed 11d ago), licensed MIT. It adds 206 tokens to every session and 15,609 once invoked, about $0.0008 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 2026-09-24.
do-ship compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| do-shipJerry0022/dotclaude | Skill | 6 | 11d ago | MIT | A | 206 | Claude Code |
| release-announcementpaperclipai/paperclip | Skill | 111k | yesterday | MIT | A | 42 | Claude Code, Codex |
| releasethedotmack/claude-mem | Skill | 114k | yesterday | Apache-2.0 | A | 13 | Claude Code |
| release-notesphuryn/pm-skills | Skill | 28k | 8d ago | MIT | A | 57 | Claude Code |
| multi-agent-release-managerchromium/chromium | Skill | 25k | yesterday | BSD-3-Clause | A | 27 | Claude Code, Codex |
| pack-submitaeonfun/aeon | Skill | 788 | yesterday | MIT | A | 27 | Claude Code, Codex |
| updater_guidesiddsachar/row-bot | Skill | 1.7k | yesterday | Apache-2.0 | A | 22 | Claude Code, Codex |