A release-closing command for a development project. It checks that planned work is finished, validates approved changes, updates architecture notes, records release metrics, and checks signals for the next cycle.

Validating release contracts, refreshing architecture.md, logging releases in releases.json, measuring shipped work and quality, and preparing the next cycle.

It gathers the checks and release records needed before closing a development cycle in one process.

ship — Command by dormstern

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/dormstern/forge/ship

Clone the repo

git clone --depth 1 https://github.com/dormstern/forge

Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 661 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	$0.00036	$0.00661
Opus 5	$0.00018	$0.00331
Sonnet 5	$0.00007	$0.00132
Haiku 4.5	$0.00004	$0.00066

Measured yesterday against content hash c6f03f71fcae, 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 yesterday.

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.

commands/ship.md · 69 lines

How it starts

The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/forge:ship — Ship & measure (PM mode)

Execution mode: direct. This command has explicit steps below — execute them in order. Do not enter plan mode, do not write a plan file, do not call ExitPlanMode. The framework already did the planning; you just run the steps.

You close out the current release cycle and prep the next one's signals.

Pre-conditions

All approved-plan features are status="done" or status="blocked". If any are still status="building", refuse and tell the user.

Behavior

Contract validation (if contract_mode != "none").
- Review every Builder-flagged BREAKING_CHANGE from this release.
- Unapproved breaking changes halt the release. Tell the user explicitly.
- Approved ones get logged in contracts.md with migration path.
Architecture auto-refresh.
- Update architecture.md with new modules, hot path changes, new endpoints, new dependencies.
- This is incremental — only touch what changed.

Log the release in releases.json. Append to releases[]:

{
  "version": "X.Y.Z",
  "name": "...",
  "thesis": "...",
  "shipped_features": [feature-ids],
  "metrics": {
    "features_shipped": N,
    "rework_rate": 0.0–1.0,
    "blocked_features": N,
    "avg_resets": float,
    "avg_quality_score": float
  },
  "identity_changes": [evolution log entries this cycle],
  "breaking_changes": [contract changes],
  "key_learnings": [from progress.md],
  "open_questions": [for next cycle]
}

Stabilization trigger check for next cycle.
- Rework rate > 15%? Blocked features ≥ 3? Avg resets > 2? Avg quality_score < 6.0?
- If any trigger fires, surface it prominently. The next /forge:shape will recommend a stabilization release.
PAUSE — Present the release report.
- Headline: version, thesis, features shipped, avg quality.
- Quality trend (vs last 2 releases).
- Identity changes (if any).
- Breaking changes (if any).
- Top 3 learnings.
- Open questions for next cycle.
- Stabilization recommendation (if triggered).

Read the full file on GitHub · 69 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.

yesterday First seen · 69 lines · 36 tokens per session scan A c6f03f71fcae

Subscribe to this mod's changes

ship is a command published in the GitHub repository dormstern/forge (6 stars, last pushed 3mo ago), licensed MIT. It adds 36 tokens to every session and 661 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.

Analytics and metrics Git and workflow Planning

ship

Getting it into your agent

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/forge:ship — Ship & measure (PM mode)

Pre-conditions

Behavior

What this file has done since we first saw it

Other commands, from other repositories

checklist

clarify

specify

analyze

converge

implement