rocket-stack · open source · MIT

Agents that prove their work.

rocket-stack is a skill pack for AI coding agents. Before your agent says “done”, it maps the mission, reviews its own code, runs a real Test Flight and saves the proof in your repo.

  • 6 skills
  • Plain-language tasks
  • Proof lives in your repo

› /rocket-mode

› add login rate limiting

Playbook: Ship → implement, review, prove

# Mission Log

Playbook: Ship

Next: /pre-flight-check login → /mission-control login

Result: Pass

Proof: mission-map/login/proof/pre-flight.md

mission-map/login/proof/dashboard.png

Note: Rate limit added; Pre-Flight Check Go; login Test Flight passed.

The problem

Agents often mark work as done without showing that it works.

The fix

rocket-stack makes proof part of “done”: no Test Flight, no proof, not done.

How it works

One mission. Five stages.
Proof at the end.

Turn on Rocket Mode and describe the task like you would to a teammate. It picks the right playbook and routes every change through the same flight path.

  1. 01 · Map

    Mission Map

    How to reach the feature, how to control it, and what proof looks like. Written once, kept in sync with the code.

    /create-mission-map
  2. 02 · Build

    Ship the change

    You type the task in plain language. Rocket Mode picks the playbook and hands the work to the right skills.

    /rocket-mode
  3. 03 · Review

    Pre-Flight Check

    A strict peer-style review of its own diff. Six checks, every finding with file:line. Go or No-go.

    /pre-flight-check
  4. 04 · Fly

    Test Flight

    One real user action that proves success, on the real surface: a UI, an API or a CLI.

    /mission-control
  5. 05 · Prove

    Mission Log

    Proof saved in your repo: the action, the result and the side effect. Pass or Fail, with the path.

    mission-map/<name>/proof/
Any Open finding is a No-go. The agent stops: not done.
Claiming done needs a Test Flight with proof: Pass/Fail plus the path.
The skill pack

Six skills. One standard of done.

Start with Rocket Mode and let it route, or call any skill directly. Each one writes only where it should and reports in a fixed format.

Start here

Rocket Mode

/rocket-mode

Turn it on and describe the task in plain language. It picks a playbook (Map first, Prove, Drift, Ship, Fix fail or Ground control), routes to the other skills and insists on proof before “done”.

Writes
Nothing itself. It routes.
Reports
Playbook · Next · Result · Proof · Note

Mission Control

/mission-control <name>

Proves one mission: updates its Mission Map if needed, runs a Test Flight and leaves a Mission Log. On a fail it still captures proof when possible.

Writes
mission-map/<name>/
Reports
Result (Pass / Fail) · Proof · Note · Updated

Create Mission Map

/create-mission-map

Interviews the repo, writes the top 3–5 missions (happy paths first, then auth, then fragile flows) and proves one with Mission Control.

Writes
mission-map/
Reports
Created · Proven · Proof · Note

Maintain Mission Map

/maintain-mission-map

Fixes drift when routes, commands, selectors or flows change. Keeps every existing proof file and lists the missions that need a new proof.

Writes
mission-map/
Reports
Changed · Reason · Re-prove
New

Pre-Flight Check

/pre-flight-check <name>

Reviews its own diff like a strict peer, before the Test Flight. Brief, Tests, Errors, Security, Readability, Debris: every finding with file:line. Any Open means No-go.

Writes
mission-map/<name>/proof/pre-flight.md
Reports
Result (Go / No-go) · Fixed · Accepted · Open · Proof · Note
New

Ground Control

/ground-control

Scans the whole repo for duplicates, dead code, missing tests, oversized files, fragile code and debris. Keeps a Space Debris list with a trend and picks the top 1–3 to fix next.

Writes
ground-control/debris.md
Reports
Open · Trend · Next · Proof
Proof, not promises

Every claim leaves a trail in your repo.

Maps and proof live in the target repo, next to the code, not in the skill pack. Anyone on the team can open them and check.

No proof, no done

A Mission Log records the action, the result and the side effect under mission-map/<name>/proof/.

Evidence or it isn’t a finding

Review findings and debris items cite file:line. No evidence, no item.

History is the trend

Proof is never deleted, and Space Debris items are never removed, only marked Fixed or Accepted.

your-app / target repoexample files
mission-map/
login/
proof/
ground-control/
mission-map/login/proof/pre-flight.md /pre-flight-check

# Pre-Flight Check: login

Change: Rate limit on POST /api/login

CheckStatusEvidence
BriefPasssrc/auth/login.ts:42 — 5 attempts/min per IP, as asked
TestsFixedtest/login.test.ts:88 — added test for 429 after 5 attempts
ErrorsPasssrc/auth/login.ts:51 — limiter store down → request allowed, error logged
SecurityPasssrc/auth/login.ts:44 — keyed by IP, no email in logs
ReadabilityPassNone
DebrisFixedsrc/auth/login.ts:60 — removed console.log
Result: Go

Replaced on every run, so it always reviews the final code.

Quick start

Ready for launch in three steps.

No build step and no config. The skills are plain folders your agent reads.

  1. Get the pack

    Clone the open-source repo from GitHub.

    $ git clone https://github.com/rocketbase-space/rocket-stack.git
  2. Install the skills

    Copy the six skill folders into the directory your agent loads skills from.

    # the six skill folders
    $ cp -r rocket-stack/*/ <your-skills-dir>/
  3. Launch

    Enable Rocket Mode, then type the task as a normal message. No flags, no forms.

    › /rocket-mode
    › add login rate limiting
Or call a skill directly: /mission-control login /create-mission-map /maintain-mission-map /pre-flight-check login /ground-control
rocket-stack · MIT

The mission succeeds
only when proven.

Give your agent the same standard you would give a teammate: show it works, then call it done.