Patton Protocol
Coordinate bounded coding-agent missions when independent delegation improves the task.
Install
npx skills add vladimirrott/patton-protocol --skill patton-protocolgit clone --depth 1 https://github.com/vladimirrott/patton-protocol.git /tmp/patton-protocol
mkdir -p ~/.claude/skills
cp -r /tmp/patton-protocol/. ~/.claude/skills/patton-protocolPersonal skills live in ~/.claude/skills. Use .claude/skills in a project folder to share a skill with your team.
From the SKILL.md
# Patton Protocol Patton Protocol is a portable Agent Skills package for coordinating bounded coding-agent missions. It targets any host that implements the Agent Skills `SKILL.md` format. The core names roles, contracts, limits, and evidence rules; the host decides how it starts workers. Patton Prime owns the lifecycle, the mission ledger, and the final decision. Prime delegates only when a delegation threshold is met: the work contains at least two independent bounded missions, each mission has a useful stopping condition, and coordination costs less than serial execution. Prime keeps one mission in the main loop when that threshold is not met. This threshold governs optional parallel delegation. Every candidate lifecycle still requires a mandatory independent read-only Verifier, which is exempt from the threshold and remains required after one Builder. Parallel Builders require independent missions with separate mutable paths. Overlapping paths force serial execution, and a no-spawn host always uses serial fallback. The mission and report contracts define the data exchanged across each lifecycle stage: [mission contract](references/mission-contract.md), [worker report](references/worker-report.md), and [safety and budgets](references/safety-and-budgets.md). The optional [harness adapter overview](references/harness-adapters.md) maps these capabilities to host surfaces. Any Agent Skills-compatible host is
Details
- Skill name
patton-protocol- Repository
- vladimirrott/patton-protocol
- License
- MIT
- Repo updated
- 27 October 2026
FAQ
What does the Patton Protocol skill do?
Coordinate bounded coding-agent missions when independent delegation improves the task.
How do I install the Patton Protocol skill?
skills CLI (Claude Code, Cursor, Codex and more): npx skills add vladimirrott/patton-protocol --skill patton-protocol. Skills go in ~/.claude/skills (personal) or .claude/skills (project), and Claude loads them automatically when a task matches the description.
Is Patton Protocol popular?
It lives in vladimirrott/patton-protocol, which has 13 GitHub stars and 0 forks.
Related skills
Meeting Scribe
9alphaparkinc/genpark-skill-meeting-scribe
Meeting Scribe — Real-time meeting intelligence agent that transcribes conversations, identifies action items, and generates multi-dimensional summaries for distribution across platforms.
Feature Marker
11Viniciuscarvalho/Feature-marker
Skill-first run-through feature workflow for Claude, Codex, and Gemini. Use when the user asks to implement a feature through PRD, TechSpec, Tasks, verification, local commit, and branch handoff. The npm package installs skill files only; the LLM skill performs the workflow.
Openclaw Genpark Inbox Liquidator
9alphaparkinc/openclaw-genpark-inbox-liquidator
OpenClaw GenPark Inbox Liquidator - Zero-inbox NLP action item and Eisenhower matrix triage engine with automated task extraction and reply drafting.
Webman
12zjkal/webman-skill
Expert skill for the webman framework (a long-lived, in-memory PHP framework based on workerman). Covers routing, controllers, middleware, database/Redis, custom processes, timers, coroutines (v2), plugin development, and guarding against memory leaks and cross-request state pollution under the resident process model. Use when the project has start.php, config/process.php, or support/bootstrap.php, or when the user mentions webman, workerman, 常驻内存 PHP, 协程 PHP, or long-lived/in-memory PHP.
Taskwarrior
9timcase/taskwarrior-agent-skill
Comprehensive task management using Taskwarrior CLI - add, modify, filter, complete, and sync tasks with support for projects, tags, priorities, due dates, dependencies, recurrence, and custom attributes (UDAs). Use when managing tasks, todos, or task lists including operations like creating tasks with attributes, filtering/querying tasks by project/tag/status/date, completing/deleting tasks, bulk operations on multiple tasks, task dependencies and blocking, recurring tasks, urgency-based prioritization, and syncing tasks with a task server.
Ironloop
10edouard-claude/ironloop
Verification-first software engineering harness with 5 layers (spec → gen → test → sim → pentest). Use when generating, reviewing, or planning code with AI agents, especially for Rust projects, new feature work, legacy migrations, or any task where code correctness must be guaranteed. Activates on phrases like "build a", "implement", "refactor", "review this code", "migrate from", "add tests for", or when the user describes a coding task with correctness or security requirements.
Browse the most popular Claude skills, all productivity & notes skills, or write your own with the skills generator.