/plan
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
$ npx -y skills add cortex-tms/cortex-tms --skill plan --agent claude-codeHow it fires
How this skill gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
- Slash command
/plan
Context preview
The summary Claude sees to decide when to auto-load this skill.
Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
SKILL.md
plan.SKILL.mdname: plan
description: Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor.
disable-model-invocation: true
allowed-tools: Read, Glob, Grep, WebSearch, WebFetch, Edit, Write, Task, EnterPlanMode, ExitPlanMode, AskUserQuestion
Plan
You are planning a feature for Cortex TMS. Enter plan mode immediately.
Rules
1. **Enter plan mode** — use EnterPlanMode before doing anything else 2. **Research first** — read relevant source files, tests, docs, and patterns before proposing anything 3. **Follow Propose/Justify/Recommend**:
- **Propose**: What you will build and how
- **Justify**: Why this approach, with evidence from the codebase
- **Recommend**: One clear recommendation — then stop and wait
4. **Write the plan** — update NEXT-TASKS.md with a sprint checklist (- [ ] items) and acceptance criteria 5. **Update task files if needed**:
- Move tasks between NEXT-TASKS.md and FUTURE-ENHANCEMENTS.md
- Update status markers in FUTURE-ENHANCEMENTS.md
- Archive completed sprints to docs/archive/
6. **Exit plan mode** — present the plan for user approval via ExitPlanMode 7. **STOP** — do not write any code. Wait for the user to approve or give feedback.
You CANNOT
- Touch any file in src/, bin/, templates/
- Edit README.md, package.json, or any config file
- Write code, tests, or build artifacts
- Run build, test, or lint commands
- Proceed to implementation without explicit user approval
Arguments
$ARGUMENTS
Read more
name: plan description: Research the codebase and create an implementation plan following Propose/Justify/Recommend. Use this before any feature, fix, or refactor. disable-model-invocation: true allowed-tools: Read, Glob, Grep, WebSearch, WebFetch, Edit, Write, Task, EnterPlanMode, ExitPlanMode, AskUserQuestion
Plan
You are planning a feature for Cortex TMS. Enter plan mode immediately.
Rules
1. **Enter plan mode** — use EnterPlanMode before doing anything else 2. **Research first** — read relevant source files, tests, docs, and patterns before proposing anything 3. **Follow Propose/Justify/Recommend**:
- **Propose**: What you will build and how
- **Justify**: Why this approach, with evidence from the codebase
- **Recommend**: One clear recommendation — then stop and wait
4. **Write the plan** — update NEXT-TASKS.md with a sprint checklist (- [ ] items) and acceptance criteria 5. **Update task files if needed**:
- Move tasks between NEXT-TASKS.md and FUTURE-ENHANCEMENTS.md
- Update status markers in FUTURE-ENHANCEMENTS.md
- Archive completed sprints to docs/archive/
6. **Exit plan mode** — present the plan for user approval via ExitPlanMode 7. **STOP** — do not write any code. Wait for the user to approve or give feedback.
You CANNOT
- Touch any file in src/, bin/, templates/
- Edit README.md, package.json, or any config file
- Write code, tests, or build artifacts
- Run build, test, or lint commands
- Proceed to implementation without explicit user approval
Arguments
$ARGUMENTS
The Universal AI-Optimized Project Boilerplate. A Tiered Memory System (TMS) designed to maximize AI agent performance. Includes an interactive CLI tool and a high-signal documentation standard.
Repo: cortex-tms/cortex-tms
Other skills on cortex-tms.
- /implement
Implement an approved plan. Write code, tests, and docs following the sprint checklist in NEXT-TASKS.md.
Open skill - /new-command
Scaffold a new CLI command for Cortex TMS following the existing codebase patterns.
Open skill - /release
Guide through the Cortex TMS release process — version bump, changelog, sync, tag, publish. Every step requires user approval.
Open skill - /sync
Synchronize task files and source-of-truth documents. Update NEXT-TASKS.md, FUTURE-ENHANCEMENTS.md, README, and CHANGELOG to reflect current project state.
Open skill - /validate
Run the full quality gate — tests, lint, build, and cortex-tms validate --strict.
Open skill