Agent Plugins Marketplace
← All plugins

claude-planner

v1.0.9

Two authority levels that separate deciding from doing. /planfirst investigates with read-only tools, probes the riskiest assumption, produces a plan in eighteen sections and STOPS. /proceed executes that plan, in sequence and within its scope, and reports against the acceptance criteria it wrote.

Claude Code2 Skills

By Ruel NopalLicense: MIT1 GitHub starsUpdated 4 days ago

Directory evidence

Runtimes
Claude Code
Parsed components
2 skill or MCP entries
Source updated
Sep 19, 2026
Manifest status
Canonical path parsed

The directory validates manifest shape and source location. It does not execute the plugin or provide a security endorsement. Review the indexing methodology →

Install claude-planner for Claude Code

Installs for the current user
claude plugin marketplace add IchenDEV/agent-plugin-mkt
claude plugin marketplace update agent-plugin-marketplace
claude plugin install claude-planner@agent-plugin-marketplace

Paste and run these commands in a terminal with Claude Code. They add and refresh the PluginsMP catalog, then install this plugin.

The installer fetches third-party code from the source repository shown on this page. This directory validates manifest structure and source location, but does not perform a security audit; review the manifest, components, and source before installing.

Get the source manually
git clone https://github.com/raketbizdev/claude-planner

Clone the source repository, then follow its setup instructions to add the plugin to a compatible client. The repository root is the plugin root.

Plugin files

claude-planner/
├── .claude-plugin/plugin.json
├── skills/planfirst/SKILL.md
└── skills/proceed/SKILL.md

Included Skills2

planfirstskills/planfirst/SKILL.md

Investigate a task thoroughly using read-only tools, check the sources are current, run one read-only probe of the riskiest assumption, then produce a detailed structured implementation plan and STOP without changing anything. Grants permission to look, never permission to edit, install, migrate, deploy, commit or fix. Nothing but an explicit /proceed authorises execution — not "yes", "ok", "go ahead" or "looks good". Use when /planfirst is invoked, or when asked to plan, scope, investigate or design an approach before any work is done.

proceedskills/proceed/SKILL.md

Execute the plan most recently produced by /planfirst, in sequence and within its scope, then test, verify against the acceptance criteria and report honestly. Refuses when no plan exists. Stops and asks again when a discovery makes the approved plan materially wrong, rather than silently changing it. Use when /proceed is invoked.

Plugin manifests1

.claude-plugin/plugin.json
{
  "name": "claude-planner",
  "description": "Two authority levels that separate deciding from doing. /planfirst investigates with read-only tools, probes the riskiest assumption, produces a plan in eighteen sections and STOPS. /proceed executes that plan, in sequence and within its scope, and reports against the acceptance criteria it wrote.",
  "version": "1.0.9",
  "author": {
    "name": "Ruel Nopal",
    "url": "https://github.com/raketbizdev"
  },
  "homepage": "https://github.com/raketbizdev/claude-planner#readme",
  "repository": "https://github.com/raketbizdev/claude-planner",
  "license": "MIT",
  "keywords": [
    "planning",
    "workflow",
    "code-review",
    "safety",
    "agent-skills"
  ]
}

For maintainers

If you maintain this plugin, link to this source-backed listing from your README so users can review its manifest and indexed components.

[claude-planner on Agent Plugins Marketplace](https://pluginsmp.com/plugins/claude-planner)