Long-running, validator-gated, fix-loop-driven multi-feature missions for Claude Code. Reverse-engineered from Factory.ai droid's /missions.
User-testing validator (v1 merged role) — plans the user-level flows for a milestone, executes them sequentially per testing surface, and writes flow reports + the user-testing synthesis.
Mission implementation worker. Implements ONE feature per spawn, commits, and writes a schema-validated handoff JSON. Generic — loads the per-mission role SKILL.md named in its prompt.
Mission orchestrator — runs the milestone-gated state machine for long-running, validator-gated multi-feature missions. Set as your session agent to drive an active mission.
Reviews ONE feature's implementation (diff + handoff vs expected behavior) and writes a schema-validated review JSON. Read-only on source; writes only its own review file.
Milestone scrutiny validator. Runs programmatic validators (test/typecheck/lint), PLANS the per-feature review fan-out (it cannot spawn reviewers), and later is re-spawned to synthesize.
Pause a mission — /missions:kill [id]. Sets state=paused; the orchestrator refuses to advance until resumed.
List this project's missions — /missions:list.
Resume a mission — /missions:resume <id-or-prefix>. Points active-mission.txt at it and re-enters the state machine from disk.
Start a new mission — /missions:start "<objective>". Creates the per-project mission control plane and enters the planning interview.
Show mission status — /missions:status [id]. One compact disk-truth snapshot.
Modifies files
Hook triggers on file write and edit operations
Uses power tools
Uses Bash, Write, or Edit tools
Own this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimOwn this plugin?
Verify ownership to unlock analytics, metadata editing, and a verified badge. GitHub access is read-only (username + org membership).
Sign in to claimBased on adoption, maintenance, documentation, and repository signals. Not a security audit or endorsement.
A Claude Code plugin marketplace for a harness-agents style development process — a set of plugins that drive development through coordinated agents, skills and lifecycle hooks.
Names (
dotclaudemarketplace and the first plugin) are provisional and will be finalized later.
dotclaude/
├── .claude-plugin/
│ └── marketplace.json # Marketplace manifest (lists all plugins)
├── plugins/ # One subdirectory per plugin
│ └── <plugin-name>/
│ ├── .claude-plugin/
│ │ └── plugin.json # Plugin manifest
│ ├── agents/ # Sub-agent definitions
│ ├── skills/ # Packaged skills
│ └── hooks/
│ └── hooks.json # Lifecycle hooks
└── README.md
Add the marketplace, then install a plugin from it:
/plugin marketplace add NicolasPalermo/dotclaude
/plugin install <plugin-name>@dotclaude
While developing locally, point the marketplace at this checkout:
/plugin marketplace add /Users/galina/work/dotclaude
None yet — the first plugin is in progress.
npx claudepluginhub nicolas-palermo/dotclaude --plugin missionsAutonomous LinkedIn job applier — discovers jobs, decides apply/skip, generates a tailored CV per posting, fills Easy Apply or external ATS forms, and logs every attempt.
Ultra-compressed communication mode. Cuts ~75% of tokens while keeping full technical accuracy by speaking like a caveman.
Multi-model consensus engine integrating OpenAI Codex CLI, Gemini CLI, and Claude CLI for collaborative code review and problem-solving.
Curate auto-memory, promote learnings to CLAUDE.md and rules, extract proven patterns into reusable skills.
Comprehensive UI/UX design plugin for mobile (iOS, Android, React Native) and web applications with design systems, accessibility, and modern patterns
Memory compression system for Claude Code - persist context across sessions