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.
git clone --depth 1 https://github.com/akka/ai-marketplaceWrote 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/commands/akka/ai-marketplace/ship)<a href="https://agentmods.dev/commands/akka/ai-marketplace/ship"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/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/commands/akka/ai-marketplace/ship"><img src="https://agentmods.dev/badge/commands/akka/ai-marketplace/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 | $0.00033 | $0.01226 |
| Opus 5 | $0.00016 | $0.00613 |
| Sonnet 5 | $0.00007 | $0.00245 |
| Haiku 4.5 | $0.00003 | $0.00123 |
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 9d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding.
Purpose
/akka:ship runs the auditors for every applicable exit condition in scope for
the requested ship target, and on pass runs the ship steps the organization
declared for that target. The target argument is REQUIRED. Two targets are
accepted:
review— runs the auditors for every applicable exit condition taggedauthororreview. On pass, runs the organization's review ship steps (typically push the branch and open a pull request).release— runs the auditors for every applicable exit condition at any tier (author,review, andrelease). On pass, runs the organization's release ship steps (typically deploy to production).
Author-time is a precondition, not a ship target. There is no /akka:ship author.
The author-time conditions are evaluated first, on their own, before any higher-tier auditor is given a chance. In À la carte mode the gate is advisory like every other condition: the run continues, every in-scope tier is evaluated, and the user gets the complete picture to override against.
In Enforced mode a ship that fails them stops right there — the review-time and release-time checks never run, so a ship that cannot succeed does not first spend minutes on scanning, dynamic analysis, or live-service probes. The user sees only the author-time verdict, which is the only one that has been computed.
An active waiver satisfies the precondition exactly as it satisfies any other condition — a waiver is a person's time-bound, recorded acceptance, not a bypass.
Outline
-
Parse the target from
$ARGUMENTS. Read the first argument. It MUST berevieworrelease. If missing, invalid, or anything else, stop and tell the user: "/akka:shiprequires an explicit target:revieworrelease. For example:/akka:ship review." Do not call the CLI. -
Invoke the CLI. Run
akka specify ship <target>in the project directory (via the shell). Capture the output. The CLI:- Runs the author-time auditors first; in Enforced mode stops there if any of them blocks.
- Otherwise runs the auditors for every remaining applicable exit condition in scope for the target.
- Reports the verdict (
READY_TO_SHIPorNOT_READY). - In À la carte mode, records an explicit override and proceeds even when
the verdict is
NOT_READY. - In Enforced mode, refuses to run any ship steps unless the verdict is
READY_TO_SHIP. - Writes a conformance receipt recording which target was shipped, what was
verified, and any conditions that remained
openwith their reasons.
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.
- 9d ago First seen · 114 lines · 33 tokens per session scan A 4f359f8c726a
ship is a command published in the GitHub repository akka/ai-marketplace (6 stars, last pushed today), licensed Apache-2.0. It adds 33 tokens to every session and 1,226 once invoked, about $0.0002 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 2026-08-31.
Other commands, from other repositories
wrap
The session-scoped landing step after ship: flips board rows, merges the operator's own green PRs one at a time, checks deploys, tidies branches and worktrees, writes the activity line, calls /kit:retro when a shipped PR merged, and prints the skim-first report. Use when the operator says to wrap up or close out the…
ship
Ship: review gate, tests, version bump, changelog, conventional commit, docs update, PR. Complete pipeline from done to merged.
ship
Run /ship — see .claude/commands/ship.md for the authoritative spec.
pr-package
Prepare a clean delivery package for GitHub from the real git diff vs an explicit base branch, persisted as PRPACKAGE.md (or PRPACKAGE. .md for multi-repo tasks). Produces branch name, commit messages, fetch, checkout, add, commit, and push commands, PR title and body, and reviewer attention points; never invents work…
land
Cadence-tick autonomous PR babysitter (CI-fix, resolve, converge, merge, close, release).
release-notes
Generate consistent, well-structured release notes from git history. Triggered on release tags following semver patterns (v..) to produce categorized changelog with breaking changes, features, fixes, and contributor attribution.