A release checklist for shipping a feature across an SDK, command-line tool, MCP tool, documentation, README files, and machine-facing API information. It requires each checklist item to be completed or explicitly marked as not applicable.

Use it before releasing a feature to check implementations, tests, docs, package instructions, API references, versioning, and builds.

It reduces the chance that a feature works in code but is missing from tests, documentation, another interface, or the public machine contract.

ship — Command by mission69b

Install

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.

agentmods

npx agentmods add commands/mission69b/t2000/ship

Clone the repo

git clone --depth 1 https://github.com/mission69b/t2000

Made for: Claude Code.

Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 750 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00020	$0.00750
Opus 5	$0.00010	$0.00375
Sonnet 5	$0.00004	$0.00150
Haiku 4.5	$0.00002	$0.00075

Measured 2d ago against content hash c9a0126c8ca2, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 2d 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.

.claude/commands/ship.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the ship checklist for: $ARGUMENTS

Work through each item. For each, either do it, or state explicitly why it doesn't apply to this slice. Don't silently skip.

Surfaces

SDK implementation + tests (packages/sdk/src/)
CLI command + tests (packages/cli/src/commands/)
MCP tool + tests (Connect — audric/apps/mcp/lib/tools.ts)
Agent Skill (t2000-skills/skills/) — only on lifecycle/policy/money-rule changes; never for Connect card/next polish (tools/list is the inventory SSOT)
Mintlify docs (apps/docs/*.mdx) — auto-deploys to docs.t2000.ai
Root README.md
Package README.mds
Machine front door — if this slice changed a machine contract (public api.t2000.ai/v1/* paths/shapes agents rely on · CLI marketplace/wallet verbs agents are told to run · Connect auth model or connector URL · discovery URLs · who can sign · earn-first/fee/ open-reject locks), update audric/apps/console/app/llms.txt/route.ts and confirm every URL it cites returns non-5xx. UI polish/copy nits don't fire the gate — write N/A. Depth: .claude/skills/t2000-machine-front-door/SKILL.md
Version bump + build all packages (/release)

Tests live inline next to source (Foo.ts + Foo.test.ts) — never add a new __tests__/ folder.

Docs cadence — two tiers, not "dump as you go"

Per-slice (now): keep docs.t2000.ai factually correct only — version, command surface, behavior (limits-on, no-charge-on-failure). Cheap; prevents the staleness class.
Per-phase (later): a dedicated structured-docs task turning the phase's specs into a story-driven product + technical section (features → benefits → how it works), not a textbook manual.

Catalog tables come from live truth, never from memory

Any docs table enumerating services / models / tools / skills MUST be written against the live source:

Store Services → api.t2000.ai/v1/services
Model catalog → api.t2000.ai/v1/models
MCP tools → audric/apps/mcp/lib/tools.ts (Connect; stdio package is deprecated/frozen)
Skills → t2000-skills/skills/
CLI defaults → the CLI source

Read the full file on GitHub · 65 lines

Changes

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.

2d ago First seen · 65 lines · 20 tokens per session scan A c9a0126c8ca2

Subscribe to this mod's changes

ship is a command published in the GitHub repository mission69b/t2000 (23 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 750 once invoked, about $0.0001 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.

Backend and APIs Git and workflow Testing agent-commerce agent-economy agent-identity agent-marketplace agent-payments x402

ship

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Surfaces

Docs cadence — two tiers, not "dump as you go"

Catalog tables come from live truth, never from memory

What this file has done since we first saw it

Other commands, from other repositories

help

mesh

find-tool

status

checklist

clarify