autopilot · sethgammon — Claude Code skill: what it does, how to install
autopilot processes queued tickets from .planning/intake/ through automated research, implementation, and verification.
MIT ★ 937 updated 2026-10-29
/plugin marketplace add SethGammon/Citadel
/plugin install citadel@citadel-localWhat autopilot does
Autopilot scans .planning/intake/ for items marked as pending, briefed, or approved. For fresh items, it reviews guidelines in AGENTS.md and CLAUDE.md, documents risks, and prepares an execution brief. It then edits project files, running typecheck commands after every single change.
The process relies on Node scripts, invoking node scripts/deliver.js during preflight and node scripts/package-delivery.js to bundle finished work with a PR link. When .planning/intake/ is missing, the skill exits cleanly and points to /do setup.
This pipeline is limited to well-defined tasks of small or medium complexity. It will not handle long multi-session epics, parallel execution, or open-ended exploratory tasks.
What it helps with
- process pending task files inside
.planning/intake/ - generate implementation briefs with scope and risk criteria
- apply code modifications while checking types after each file update
- package finished deliverables and attach PR review links
Example prompts for the agent
- /autopilot
- Process the next pending item in
.planning/intake/ - Run the delivery pipeline on
.planning/intake/feature.md
How to install autopilot
1Plugin marketplace
/plugin marketplace add SethGammon/Citadel/plugin install citadel@citadel-localThis installs the whole citadel plugin with all its skills
2Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill autopilot -a claude-code3Manually: put the files in place
~/.claude/skills/autopilot/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/autopilot/
1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill autopilot -a codex2Manually: put the files in place
.agents/skills/autopilot/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill autopilot -a cursor2Manually: put the files in place
.cursor/skills/autopilot/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install SethGammon/Citadel skills/autopilot2Manually: put the files in place
.github/skills/autopilot/SKILL.md1Skills CLI (Vercel)
npx skills add SethGammon/Citadel --skill autopilot -a gemini-cli2Platform CLI
gemini skills install https://github.com/SethGammon/Citadel --path skills/autopilotManually: put the files in place
.devin/skills/autopilot/SKILL.mdThe legacy .windsurf/skills/ path still works
Claude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about autopilot
How to install autopilot in Claude Code?
Run /plugin marketplace add SethGammon/Citadel and then /plugin install citadel@citadel-local. You can also install it using npx skills add SethGammon/Citadel --skill autopilot -a claude-code.
What does autopilot do?
It reads tasks from .planning/intake/, creates structured briefs, edits code with continuous typecheck verification, and packages results.
When should autopilot not be used?
Avoid using it for multi-session campaigns, parallel workloads, or exploratory tickets without explicit requirements.
Source text
SKILL.md · MIT
---
name: autopilot
license: MIT
description: >-
Intake-to-delivery pipeline. Processes pending items from .planning/intake/:
briefs new ideas, executes approved work through research → plan → build → verify.
Drop a file in .planning/intake/ and invoke this skill.
user-invocable: true
auto-trigger: false
trigger_keywords:
- intake
- process pending
- pipeline
last-updated: 2026-03-20
---
# /autopilot — Intake Pipeline
## Orientation
Use Autopilot when:
- There are pending items in `.planning/intake/`
- You want to process intake items without manual orchestration
- The work is scoped and well-defined (Small or Medium complexity)
Do NOT use Autopilot for:
- Large, multi-session campaigns (use Archon)
- Parallel execution (use Fleet)
- Exploratory or open-ended work (use Marshal)
## Protocol
### Step 0: DELIVERY PREFLIGHT
When the user names a specific intake file or asks for "intake to PR", prefer
the deterministic delivery preflight before freeform build work:
```bash
node scripts/deliver.js --intake .planning/intake/{item}.md
```
If no specific intake file is named, use:
```
node scripts/deliver.js --next
```
This selects the highest-priority pending item in `.planning/intake/` and keeps
the golden path deterministic.
This creates an active campaign with claimed scope, acceptance criteria, map
context, and exit evidence rows, then marks the intake item `in-progress`.
Continue from the created campaign with `/do continue`.
After build and verification, package the delivery before marking the campaign
complete:
```bash
node scripts/package-delivery.js {campaign-slug}
```
If a PR exists, record the PR as the review target:
```bash
node scripts/package-delivery.js {campaign-slug} --pr https://github.com/{owner}/{repo}/pull/{number}
```
### Step 1: SCAN
Read all files in `.planning/intake/` and identify:
- `status: pending` → needs briefing
- `status: briefed` → ready to build
- `status: approved` → ready to build
- `status: in-progress` → check if stuck
### Step 2: BRIEF (for pending items)
For each pending item:
1. Read the intake file
2. Read related files mentioned in the description
3. Research the scope: what files exist, what patterns are established
4. Write the brief:
- **Scope**: Small / Medium / Large
- **Approach**: How to implement (2-3 sentences)
- **Files**: Which files to create or modify
- **Quality gates**: What must be true when done
- **Risks**: What could go wrong
5. Update the item's status to `briefed`
### Step 3: BUILD (for briefed/approved items)
For each briefed item (smallest first):
1. Read the brief
2. Execute the approach:
- Create or modify the listed files
- Follow the project's conventions (CLAUDE.md)
- Run typecheck after each change
3. Verify:
- All quality gates pass
- Typecheck clean
- Tests pass (if applicable)
4. Update status to `completed`
### Step 4: REPORT
Output a summary of what was processed:
```
Autopilot processed {N} items:
✓ {item-1}: briefed → built → verified
✓ {item-2}: briefed
✗ {item-3}: blocked — {reason}
```
## Intake Item Format
```markdown
---
title: "Feature Name"
status: pending | briefed | approved | in-progress | completed
priority: normal | high
target: src/path/to/affected/area/
---
Description of what needs to be done...
```
## Fringe Cases
- **`.planning/intake/` is empty or does not exist**: Output "Nothing to process — `.planning/intake/` is empty. Drop a file there or run `/do setup` to initialize." Do not error.
- **Intake item has no clear action**: If the description is too vague to execute, ask the user one clarifying question or skip the item with a note: "Skipped — direction unclear. Update the intake file and re-run."
- **Item status is unrecognized**: Treat unknown statuses as `pending` and proceed through the brief → build flow.
- **Typecheck fails during build**: Record the failure in the item's status, move on to the next item, and report the blocker in the exit summary.
- **`.planning/` does not exist**: Output a setup hint and exit cleanly. Autopilot requires `.planning/intake/` to operate — if the directory is absent, treat as empty intake and suggest running `/do setup`.
## Contextual Gates
**Disclosure:** "Processing intake queue: N items pending. Will dispatch skills per item."
**Reversibility:** amber — processes intake items by dispatching other skills that may modify files; undo depends on dispatched skills
**Trust gates:**
- Any: review intake and briefing.
- Familiar (5+ sessions): autopilot runs autonomously on queued items; novices should review intake before running.
## Quality Gates
- Never build without reading the project guidance (AGENTS.md, then CLAUDE.md) first
- Run typecheck after every file change
- Mark items as completed only when verification passes
- If an item is blocked, record the reason and move on
## Exit Protocol
```
---HANDOFF---
- Processed {N} intake items
- Built: {list of completed items}
- Blocked: {list with reasons}
- Remaining: {count of items still pending}
---
```
© SethGammon · MIT · SethGammon/Citadel
Similar skills
All skills for Agent setup: memory, context, orchestration →autopilot by other authors comes first.