run-plan — Claude Code command: what it does, how to install
run-plan executes a PLAN.md file directly without loading planner skill overhead. It routes tasks to subagents and keeps most of the context window free.
MIT ★ 1,988 updated 2026-04-01
/plugin marketplace add glittercowboy/taches-cc-resources
/plugin install taches-cc-resources@taches-cc-resourcesWhat run-plan does
The command reads a target plan and picks an execution strategy based on checkpoint tags. If no checkpoints are detected, it spins up a single subagent to complete all tasks, generate SUMMARY.md, and commit the changes under feat({phase}-{plan}): [summary].
When verify-only checkpoints are found, it splits execution into segments and pauses for human confirmation. Total context overhead stays under 30% (5–7k tokens for instructions and 10–15k for project context), reserving 70%+ for code modifications. If the file at plan_path is missing, the command stops immediately with an error.
What it helps with
- execute a prepared PLAN.md without loading planner prompt context
- delegate task blocks to subagents to save primary context space
- produce SUMMARY.md and structured git commits automatically
- halt automated execution at verification checkpoints for review
Example prompts for the agent
- /run-plan .planning/phases/07-sidebar/07-01-PLAN.md
- /run-plan plans/auth-migration-PLAN.md
How to install run-plan
1Plugin marketplace
/plugin marketplace add glittercowboy/taches-cc-resources/plugin install taches-cc-resources@taches-cc-resources2Manually: put the files in place
.claude/commands/run-plan.mdCall it with /run-plan. For all projects use ~/.claude/commands/
Manually: put the files in place
~/.codex/prompts/run-plan.mdCall it with /prompts:run-plan. Codex marks this format deprecated in favour of skills
Manually: put the files in place
.github/prompts/run-plan.prompt.mdManually: put the files in place
.gemini/commands/run-plan.tomlGemini stores commands as TOML: the prompt text goes into the prompt field
Questions about run-plan
How to install run-plan in Claude Code?
Add the marketplace source with /plugin marketplace add glittercowboy/taches-cc-resources, then run /plugin install taches-cc-resources@taches-cc-resources. Alternatively, place the file directly at .claude/commands/run-plan.md.
What does run-plan do?
It reads an existing PLAN.md, inspects it for checkpoint tags, and runs the tasks either via autonomous subagents or via segmented execution with human verification.
How does run-plan handle already executed plans?
It looks for a matching SUMMARY.md in the plan directory. If found, it alerts you that the plan ran previously and asks for confirmation before re-running.
Source text
run-plan.md · MIT
---
type: prompt
description: Execute a PLAN.md file directly without loading planning skill context
arguments:
- name: plan_path
description: Path to PLAN.md file (e.g., .planning/phases/07-sidebar-reorganization/07-01-PLAN.md)
required: true
---
Execute the plan at {{plan_path}} using **intelligent segmentation** for optimal quality.
**Process:**
1. **Verify plan exists and is unexecuted:**
- Read {{plan_path}}
- Check if corresponding SUMMARY.md exists in same directory
- If SUMMARY exists: inform user plan already executed, ask if they want to re-run
- If plan doesn't exist: error and exit
2. **Parse plan and determine execution strategy:**
- Extract `<objective>`, `<execution_context>`, `<context>`, `<tasks>`, `<verification>`, `<success_criteria>` sections
- Analyze checkpoint structure: `grep "type=\"checkpoint" {{plan_path}}`
- Determine routing strategy:
**Strategy A: Fully Autonomous (no checkpoints)**
- Spawn single subagent to execute entire plan
- Subagent reads plan, executes all tasks, creates SUMMARY, commits
- Main context: Orchestration only (~5% usage)
- Go to step 3A
**Strategy B: Segmented Execution (has verify-only checkpoints)**
- Parse into segments separated by checkpoints
- Check if checkpoints are verify-only (checkpoint:human-verify)
- If all checkpoints are verify-only: segment execution enabled
- Go to step 3B
**Strategy C: Decision-Dependent (has decision/action checkpoints)**
- Has checkpoint:decision or checkpoint:human-action checkpoints
- Following tasks depend on checkpoint outcomes
- Must execute sequentially in main context
- Go to step 3C
3. **Execute based on strategy:**
**3A: Fully Autonomous Execution**
```
Spawn Task tool (subagent_type="general-purpose"):
Prompt: "Execute plan at {{plan_path}}
This is a fully autonomous plan (no checkpoints).
- Read the plan for full objective, context, and tasks
- Execute ALL tasks sequentially
- Follow all deviation rules and authentication gate protocols
- Create SUMMARY.md in same directory as PLAN.md
- Update ROADMAP.md plan count
- Commit with format: feat({phase}-{plan}): [summary]
- Report: tasks completed, files modified, commit hash"
Wait for completion → Done
```
**3B: Segmented Execution (verify-only checkpoints)**
```
For each segment (autonomous block between checkpoints):
IF segment is autonomous:
Spawn subagent:
"Execute tasks [X-Y] from {{plan_path}}
Read plan for context and deviation rules.
DO NOT create SUMMARY or commit.
Report: tasks done, files modified, deviations"
Wait for subagent completion
Capture results
ELSE IF task is checkpoint:
Execute in main context:
- Load checkpoint task details
- Present checkpoint to user (action/verify/decision)
- Wait for user response
- Continue to next segment
After all segments complete:
- Aggregate results from all segments
- Create SUMMARY.md with aggregated data
- Update ROADMAP.md
- Commit all changes
- Done
```
**3C: Decision-Dependent Execution**
```
Execute in main context:
Read execution context from plan <execution_context> section
Read domain context from plan <context> section
For each task in <tasks>:
IF type="auto": execute in main, track deviations
IF type="checkpoint:*": execute in main, wait for user
After all tasks:
- Create SUMMARY.md
- Update ROADMAP.md
- Commit
- Done
```
4. **Summary and completion:**
- Verify SUMMARY.md created
- Verify commit successful
- Present completion message with next steps
**Critical Rules:**
- **Read execution_context first:** Always load files from `<execution_context>` section before executing
- **Minimal context loading:** Only read files explicitly mentioned in `<execution_context>` and `<context>` sections
- **No skill invocation:** Execute directly using native tools - don't invoke create-plans skill
- **All deviations tracked:** Apply deviation rules from execute-phase.md, document everything in Summary
- **Checkpoints are blocking:** Never skip user interaction for checkpoint tasks
- **Verification is mandatory:** Don't mark complete without running verification checks
- **Follow execute-phase.md protocol:** Loaded context contains all execution instructions
**Context Efficiency Target:**
- Execution context: ~5-7k tokens (execute-phase.md, summary.md, checkpoints.md if needed)
- Domain context: ~10-15k tokens (BRIEF, ROADMAP, codebase files)
- Total overhead: <30% context, reserving 70%+ for workspace and implementation
© Lex Christopherson · MIT · glittercowboy/taches-cc-resources