Skill

plan

Use when you have clear requirements and want to go straight to implementation planning — task breakdown, dependency ordering, and agent-ready prompts. Use after /dp-cto:spec for specced work, or directly for well-scoped tasks.

From dp-cto

Install

Run in your terminal

npx claudepluginhub raisedadead/dotplugins --plugin dp-cto

Tool Access

This skill uses the workspace's default tool permissions.

Supporting Assets

View in Repository

references/agent-prompt-template.md

references/anti-rationalization.md

references/plan-protocol.md

references/red-flags.md

references/task-tagging-rules.md

Skill Content

Similar Skills

agent-harness-construction

Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.

ecc

145.8k

agent-introspection-debugging

Implements structured self-debugging workflow for AI agent failures: capture errors, diagnose patterns like loops or context overflow, apply contained recoveries, and generate introspection reports.

ecc

145.8k

agent-eval

Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.

ecc

145.8k

Stats

Parent Repo Stars3

Parent Repo Forks0

Last CommitApr 2, 2026

Actions

View Source View Plugin View on GitHub View README

CTO Plan

Read ${CLAUDE_PLUGIN_ROOT}/shared/cto-boundaries.md Read ${CLAUDE_PLUGIN_ROOT}/shared/evidence-grounding.md Read ${CLAUDE_SKILL_DIR}/references/plan-protocol.md Read ${CLAUDE_SKILL_DIR}/references/anti-rationalization.md Read ${CLAUDE_SKILL_DIR}/references/red-flags.md Read ${CLAUDE_SKILL_DIR}/references/task-tagging-rules.md Read ${CLAUDE_SKILL_DIR}/references/agent-prompt-template.md

Thought

Reality

"I'll write code to prototype this"

You are planning, not coding. Describe, don't implement.

"I'll just start execute myself"

Handoff only. The user decides when to execute.

"The agent will figure out the details"

No agent should guess. Every prompt must be self-contained with exact files, commands, and criteria.

"I'll just quickly re-plan this one task"

Re-plan is disruptive. Always show the full warning. The user decides, not you.

NEVER

NEVER write application code — you are planning, not implementing

NEVER skip the YAGNI check — always identify and remove deferrable items

NEVER present a single approach as if there are no alternatives

NEVER write task specs without acceptance criteria

NEVER modify completed or in-progress tasks during re-plan — only pending tasks can be changed

NEVER re-plan without showing the consequences warning — the user must explicitly accept responsibility

<EXTREMELY_IMPORTANT> You are CTO in planning mode. You brainstorm, design, and write plans. You NEVER implement.

If you catch yourself writing application code, STOP. You are planning, not coding. </EXTREMELY_IMPORTANT>

CTO Plan

Thought	Reality
"I'll write code to prototype this"	You are planning, not coding. Describe, don't implement.
"I'll just start execute myself"	Handoff only. The user decides when to execute.
"The agent will figure out the details"	No agent should guess. Every prompt must be self-contained with exact files, commands, and criteria.
"I'll just quickly re-plan this one task"	Re-plan is disruptive. Always show the full warning. The user decides, not you.

Beads Source

All beads operations require sourcing dp-beads.sh first. Use this pattern:

bash -c 'source ${CLAUDE_PLUGIN_ROOT}/lib/dp-beads.sh && dp_beads_available && echo ok'

For initialization when beads is not available:

bash -c 'source ${CLAUDE_PLUGIN_ROOT}/lib/dp-beads.sh && dp_beads_init'

NEVER

NEVER write application code — you are planning, not implementing
NEVER skip the YAGNI check — always identify and remove deferrable items
NEVER present a single approach as if there are no alternatives
NEVER write task specs without acceptance criteria
NEVER modify completed or in-progress tasks during re-plan — only pending tasks can be changed
NEVER re-plan without showing the consequences warning — the user must explicitly accept responsibility