بنقرة واحدة
plan
// OPT-IN file-based planning for multi-session tasks. Only use when user explicitly requests it or work spans multiple sessions. For single-session work, prefer your platform's native planning features.
// OPT-IN file-based planning for multi-session tasks. Only use when user explicitly requests it or work spans multiple sessions. For single-session work, prefer your platform's native planning features.
| name | plan |
| description | OPT-IN file-based planning for multi-session tasks. Only use when user explicitly requests it or work spans multiple sessions. For single-session work, prefer your platform's native planning features. |
| disable-model-invocation | true |
./bin/ci.sh, pytest tests/cypher_tck -xvs, and python -m tests.cypher_tck.report.plans/<task>/ (already gitignored here).For single-session work, prefer your AI platform's built-in planning features. This file-based approach adds overhead that's only justified for specific scenarios.
Only use this file-based plan template when:
plans/[task_name]/plan.md[placeholders] with actual valuesTHIS PLAN MUST BE:
REMEMBER: External memory is unreliable. This plan is your ONLY memory.
BEFORE EVERY SINGLE ACTION:
cat plans/[task_name]/plan.md | head -200tail -50 plans/[task_name]/plan.md# [Task Name] Plan
**THIS PLAN FILE**: `plans/[task_name]/plan.md`
**Created**: [DATE TIME TIMEZONE]
**Current Branch**: [from `git branch --show-current`]
**PRs**: [PR number + title + plan role]
**PR Target Branch**: [where this will merge]
**Base branch**: [FILL ME IN, TYPICALLY PR TARGET BRANCH]
## Context (READ-ONLY)
### Plan Overview
**Raw Prompt**: [What the user said, verbatim]
**Goal**: [What we're trying to achieve]
**Description**: [Brief description of the task]
**Success Criteria**: [How we know we're done]
**Key Constraints**: [Important limitations or requirements]
### Technical Context
**Initial State**:
- Working Directory: [pwd output]
- Current Branch: `[branch-name]` (forked from `[parent]` at `[SHA]`)
- Target Branch: `[where this merges to]`
### Strategy
**Approach**: [High-level plan]
**Key Decisions**:
- [Decision 1]: [Reasoning]
- [Decision 2]: [Reasoning]
## Quick Reference
```bash
# Reload plan
cat plans/[task_name]/plan.md | head -200
# Local validation before pushing
./bin/ci.sh
pytest tests/cypher_tck -xvs
python -m tests.cypher_tck.report
# CI monitoring
gh pr checks [PR] --watch
Status: IN_PROGRESS Action: [What to do] Success Criteria: [How to verify] Result:
[Fill in with commands, output, decisions, errors]
Status: TODO Action: [What to do] Success Criteria: [How to verify]
## Step Compaction
**Every ~30 completed steps, compact the plan:**
1. Create history file: `plans/[task_name]/history/steps<start>-to-<end>.md`
2. Replace archived steps with summary in plan
3. Continue with next step number