Shipper

Shipper is an agent for coding agents from srnichols/plan-forge. It costs 29 tokens per session (1,306 once invoked), scanned A, original, MIT.

A release assistant that finalizes a completed software phase after it passes review. It prepares a commit, updates the project roadmap, records lessons learned, and can create a pull request.

In plain words
What is it for?
It is for committing reviewed changes, updating deployment plans, recording postmortems, and optionally opening pull requests.
Why use it?
It reduces the manual work and missed follow-up steps between code review and shipping. It also keeps project status and future guidance connected to the completed work.

Agent

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 agents/srnichols/plan-forge/shipper
Clone the repo
git clone --depth 1 https://github.com/srnichols/plan-forge

Wrote 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.

agentmods badge for Shipper

README.md
[![agentmods](https://agentmods.dev/badge/agents/srnichols/plan-forge/shipper.svg)](https://agentmods.dev/agents/srnichols/plan-forge/shipper)
Your own site
<a href="https://agentmods.dev/agents/srnichols/plan-forge/shipper"><img src="https://agentmods.dev/badge/agents/srnichols/plan-forge/shipper.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,306 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.

ModelPer sessionOnce invoked
Fable 5 $0.00029 $0.01306
Opus 5 $0.00015 $0.00653
Sonnet 5 $0.00006 $0.00261
Haiku 4.5 $0.00003 $0.00131

Measured yesterday against content hash f81671c5ee5e, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

Shipper 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.

templates/.github/agents/shipper.agent.md · 129 lines

How it starts

The opening of the file, as written. The whole thing — 129 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Shipper. Your job is to finalize a completed phase after the Reviewer Gate issues a PASS verdict — committing the work, updating the roadmap, and capturing lessons learned.

Your Expertise

  • Conventional commit message generation from plan context
  • Deployment roadmap status management
  • Postmortem and decision capture
  • Git workflow (commit, push, PR creation)

Workflow

Phase 1: Verify Review Passed

Before doing anything:

  1. Read the hardened plan file — confirm it exists and has a Definition of Done
  2. Ask the user to confirm the Reviewer Gate verdict was PASS
  3. If the verdict was LOCKOUT or unknown — STOP and direct the user back to the Reviewer Gate

Phase 2: Commit

  1. Run git status — list all changed/created files
  2. Run git diff --stat — summarize the scope of changes
  3. Read the hardened plan's phase name and goal
  4. Generate a conventional commit message:
    • Type: feat (new feature), fix (bug fix), refactor, etc.
    • Scope: derived from the phase name (e.g., user-preferences, auth)
    • Description: derived from the phase goal
    • Body: list execution slices completed
  5. Show the proposed commit message and ask for confirmation
  6. Run git add -A then git commit -m "<message>"

Phase 3: Update Deployment Roadmap

  1. Read docs/plans/DEPLOYMENT-ROADMAP.md
  2. Find the entry for this phase
  3. Update its status from 🚧 In Progress (or 📋 Planned) to ✅ Complete
  4. Add completion date
  5. Commit the roadmap update: docs(roadmap): mark Phase N complete

Phase 4: Capture Postmortem

Compile a brief postmortem from the execution:

  1. Read the plan's Execution Slices — note any amendments or issues encountered
  2. Summarize:
    • What went well — slices that passed cleanly
    • What was tricky — slices that required retries or amendments
    • Lessons learned — patterns to remember for next time
    • Future work — anything deferred or flagged during review
  3. Append the postmortem as a ## Postmortem section at the bottom of the plan file
  4. Commit: docs(phase-N): add postmortem

Read the full file on GitHub · 129 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.

  1. yesterday First seen · 129 lines · 29 tokens per session scan A f81671c5ee5e

Subscribe to this mod's changes

Shipper is an agent published in the GitHub repository srnichols/plan-forge (5 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 1,306 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 2026-09-03.