A plugin for structured implementation planning, review, and plan execution. It can retry failed tasks and run repeated fix-and-check cycles.

Creating implementation plans, reviewing changes with an internal or external code-review command, retrying failed tasks, and executing planned work.

It gives coding work a reviewable sequence and provides settings for handling failed tasks and repeated quality checks.

planning — Plugin by umputun

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Claude Code

/plugin marketplace add umputun/cc-thingz

agentmods

npx agentmods add plugins/umputun/cc-thingz/planning

Clone the repo

git clone --depth 1 https://github.com/umputun/cc-thingz

Made for: Claude Code.

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. Scan, not verified.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

planning scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

plugins/planning/.claude-plugin/plugin.json · 50 lines

What it actually says

{
  "name": "planning",
  "description": "Structured implementation planning, interactive annotation review, and autonomous plan execution",
  "version": "3.10.0",
  "author": {
    "name": "Umputun"
  },
  "homepage": "https://github.com/umputun/cc-thingz",
  "repository": "https://github.com/umputun/cc-thingz",
  "license": "MIT",
  "userConfig": {
    "external_review_cmd": {
      "title": "External review command",
      "type": "string",
      "description": "Command for external code review tool. The prompt is appended as the final argument; findings go to stdout tagged CRITICAL/MAJOR/MINOR. Leave empty to use codex.",
      "default": ""
    },
    "task_retries": {
      "title": "Task retries",
      "type": "number",
      "description": "Number of retries for failed tasks before stopping.",
      "default": 1
    },
    "review_iterations": {
      "title": "Review iterations",
      "type": "number",
      "description": "Max fix-and-recheck cycles during internal review.",
      "default": 5
    },
    "external_review_iterations": {
      "title": "External review iterations",
      "type": "number",
      "description": "Max iterations for external review adversarial loop. The loop exits early once an iteration finds no critical/major issues.",
      "default": 10
    },
    "finalize_enabled": {
      "title": "Enable finalize",
      "type": "boolean",
      "description": "Whether to run the finalize phase (rebase and squash commits).",
      "default": true
    },
    "plans_dir": {
      "title": "Plans directory",
      "type": "string",
      "description": "Directory where plan files are located, relative to project root.",
      "default": "docs/plans"
    }
  }
}

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

yesterday First seen · 50 lines scan A 6e69bf536ec3

Subscribe to this mod's changes

planning is a plugin published in the GitHub repository umputun/cc-thingz (460 stars, last pushed 7d ago), licensed MIT. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Code review Planning claude-code claude-code-plugin marketplace plugin

planning

Getting it into your agent

Grade A, and why

Nothing flagged

What it actually says

What this file has done since we first saw it

Other plugins, from other repositories

smalltalk-dev-marketplace

smalltalk-dev

agenthub

bankstatemently

bankstatemently

luopan