Sponsor Suno AI Music arrow_forward
Slash Command

Mission

Run full attune lifecycle as a mission with state detection and phase routing

Type
Slash Command
GitHub stars
339
License
MIT
Repo last updated
Sep 24, 2026

What Mission is

Mission is a slash command published in the athola/claude-night-market repository on GitHub, which has about 339 stars. The repository describes itself as: “23 Claude Code plugins: TDD enforcement hooks, git/PR workflows, spec-driven development, code review, project lifecycle, fix-from-error, maintenance automation, context optimization, research, and multi-LLM delegation. 186 skills, 128 commands, 54 agents.”

A slash command is a reusable prompt saved as a markdown file and run by typing its name after a slash. In Claude Code, custom commands have been merged into skills: a file in .claude/commands/ and a skill folder in .claude/skills/ both create the same kind of command, and existing command files keep working.

Mission gives you a repeatable way to run the same instructions without retyping them, optionally with arguments.

How to install Mission

Claude Code

  1. Download mission.md from the repository.
  2. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md.
  3. Run it by typing / followed by its name.

Claude Cowork

  1. Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it.
  2. In Customize → Skills, click +, then upload the ZIP.
  3. Run it from any task with / and the skill name.

New to extending Cowork? Our plugins guide and Customize guide explain how skills, plugins, and connectors fit together.

Inside the source file

An excerpt from plugins/attune/commands/mission.md, shared under the repository's MIT license. Read the full file on GitHub.

Orchestrate the entire attune development lifecycle (brainstorm, specify, plan, execute) as a single mission with automatic state detection and recovery.

When To Use

Use this command when you need to:

  • Start a new project and run through the full development lifecycle
  • Resume an interrupted project workflow from where you left off
  • Execute a focused tactical implementation from existing artifacts
  • Quick-fix from an existing implementation plan
  • Audit, dogfood, or review existing software and produce a findings report

When NOT To Use

Avoid this command if:

  • You want to run a single phase without auto-chaining (use /attune:brainstorm --standalone, /attune:specify --standalone, etc.)
  • Task is non-project work (debugging, ad-hoc research). Structured review work is in scope: use --type review
  • You need fine-grained control over each phase transition

> Note: Individual commands (/brainstorm, /specify, /blueprint) now auto-chain forward by default. Use --standalone to run a single phase without continuing. Use /attune:mission when you need state persistence, resume support, and damage-control.

Usage

# Auto-detect mission type and start
/attune:mission

# Resume a paused or interrupted mission
/attune:mission --resume

# Override mission type
/attune:mission --type full
/attune:mission --type standard
/attune:mission --type tactical
/attune:mission --type quickfix
/attune:mission --type review

# Custom phase sequence
/attune:mission --phases brainstorm,execute

# Skip user checkpoints between phases
/attune:mission --auto

What This Command Does

  1. Detects project state: scans for existing artifacts (brief, spec, plan)
  2. Selects mission type: chooses the appropriate phase sequence
  3. Routes through phases: invokes Skill(attune:{phase}) for each step
  4. Checkpoints between phases: lets you review, pause, or adjust
  5. Handles errors: recovers from failures via leyline:damage-control
  6. Saves mission state: enables resume from any point

Mission Types

review is for observational work: the deliverable is a findings-and-recommendations report at reports/ - .md, not implemented code. It needs no build artifacts as input, and it skips the war-room gate, which exists to guard a plan-to-execute transition a review mission does not have. It is selected from the wording of the request rather than from artifacts on disk, because a directory full of specs and plans looks identical whether you mean to ship it or audit it.

Workflow

# 1. Invoke mission orchestrator skill
Skill(attune:mission-orchestrator)

# 2. Orchestrator detects state and selects type:
#    "Detected: specification.md exists → tactical mission"

# 3. Routes through phases:
#    Phase 1: plan
#      → Skill(attune:project-planning)
#      → Produces: docs/implementation-plan.md
#      → Checkpoint: "Continue to execute? [Y/n]"
#
#    Phase 2: execute
#      → Skill(attune:project-execution)
#      → Produces: implemented code + tests

# 4. Mission complete, state saved to .attune/mission-state.json

Session Recovery

Mission state is automatically saved to .attune/mission-state.json.

# Resume after interruption
/attune:mission --resume

# Force-resume a failed mission (resets failed phase)
/attune:mission --resume --force

The resume command:

  1. Loads saved mission state
  2. Validates artifacts still exist
  3. Continues from the last completed phase
  4. Displays a summary of progress so far

Arguments

Integration with Full Cycle

/attune:mission              ← Orchestrates everything below
  ├─ /attune:brainstorm      ← Phase 1 (if full)
  ├─ /attune:specify         ← Phase 2 (if full/standard)
  ├─ /attune:blueprint       ← Phase 3 (if full/standard/tactical)
  └─ /attune:execute         ← Phase 4 (always)

The mission command wraps the existing phase commands: you can still use individual commands for fine-grained control.

Examples

Example 1: Full New Project

/attune:mission
# Auto-detects: no artifacts → full mission
# Runs: brainstorm → specify → plan → execute

Before you install

  • Read the whole file first. Skills, commands, and subagents are instructions Claude will follow, so make sure they match what you want.
  • Check which tools, scripts, or MCP servers it uses. Local servers and scripts run with your permissions.
  • Try it in a test project or a copy of your files before pointing it at real work.
  • Pin the version you tested, and review changes before updating.
  • Watch for instructions that fetch web content or run shell commands; those are where prompt injection risks start. See our prompt injection guide.

FAQ

What is Mission?

Mission is a slash command for Claude Code and Claude Cowork from the athola/claude-night-market repository on GitHub. Run full attune lifecycle as a mission with state detection and phase routing

How do I install Mission in Claude Code?

Download mission.md from the repository. Save it to ~/.claude/commands/ (all projects) or .claude/commands/ (one project). As a skill, you can instead save it as ~/.claude/skills/<name>/SKILL.md. Run it by typing / followed by its name.

Can I use Mission in Claude Cowork?

Turn the command into a skill: create a folder with the file saved as SKILL.md and zip it. In Customize → Skills, click +, then upload the ZIP. Run it from any task with / and the skill name.

Is Mission safe to install?

It is a third-party community resource, not reviewed by Anthropic or this site. Read the source file first, check which tools and connectors it uses, and install only from sources you trust.

Similar resources

Browse all skills, subagents, and plugins →

Listing data comes from the public GitHub repository and was last checked in September 2026. Excerpts are © their authors and shared under MIT. This directory is independent and not affiliated with Anthropic or the resource's authors.