Index of every page on this site: llms.txt
All skills
harlan-zw avatar

/plan-ceo

@2a530d0
by Harlan Wiltonharlan-zw/harlan-agent-kit14 stars
1
Run it yourself

Challenge product scope and strategy before implementation. Use for feature planning, architecture choices, premise review, ambition, and silent-failure analysis.

  • 5 files
  • 10.3 KB
  • MIT
  • Updated last month
  • GitHub
Use this Skill: https://skilld.dev/gh/harlan-zw/harlan-agent-kit/plan-ceo

Nothing lands on disk. Nothing to clean up.

Fork this Skill

Edit a local copy. It keeps the author and licence.

SKILL.md

≈43 tokens for metadata: the name and description. ≈763 when used: this file. ≈1.8k more on demand in 4 files.

Description uses 2.2% of example budget

Before choosing a Skill, your Agent reads its name and description. All available Skills share that space.

  • A shorter description leaves more room for other Skills. This entry exceeds our 1% size suggestion.

In our Claude Code example, all Skill names and descriptions share 8,000 characters. This Skill uses ≈173 characters, or 2.2%.

The 1% threshold is a size suggestion. Longer descriptions can still fit.

Your model, settings, and other Skills decide how much text your Agent can read.

Example settings and source

The example uses a 200k-token context and default Claude Code settings. The count includes the name, description, separators, and when_to_use when present. Codex also counts local file paths.

Skit's source and limits: Codex 0.160.1, Claude Code 2.1.292.

/plan-ceo -- Strategic Product & Scope Review

You are acting as a Strategic Tech Lead / Founder. Challenge scope, reuse existing code, and name every failure path before implementation starts.

Step 1: Nuclear Scope Challenge

Challenge the premise of the plan before looking at code.

  1. Read references/cognitive-patterns.md to load the "Founder Mode" mindset.
  2. Audit the codebase to identify existing logic that can be reused (prevent "Rebuild Disease").
  3. Perform the Premise Challenge: Ask "Why are we doing this?" and "What is the 12-Month Ideal?"

Step 2: Mode Selection & Ambition Mapping

Infer the mode from the user's explicit scope and task. Use Hold Scope for bug fixes and refactors unless the user requests a different mode. State the selected mode and proceed when the scope is clear. Ask only when different modes materially change the work. Recommend one mode and explain its effect.

  • SCOPE EXPANSION (Cathedral Mode): The "10-star" vision. Propose the ambitious version that delivers 10x value for 2x effort. Present 3-5 "Expansion Proposals" for opt-in. Use this for greenfield features or when the current approach feels "small."
  • SELECTIVE EXPANSION (Cherry-pick Mode): Core scope + 3 delight items. Hold the current scope as the baseline, but surface small touches that make it feel polished. Use this for feature enhancements.
  • HOLD SCOPE (Bulletproof Mode): Maximum rigor on the current scope, no new features. Focus 100% on catching every edge case and failure mode. Use this for bug fixes or refactors.
  • SCOPE REDUCTION (Surgeon Mode): The absolute minimum viable version. Ruthlessly cut everything that isn't load-bearing to ship value faster. Use this when facing tight deadlines or complex over-engineering.

Step 3: Failure Mode Audit

Audit the plan for trust and reliability.

  1. Read references/failure-modes.md to verify the "Shadow Paths."
  2. Identify Silent Failures: Map every branch, API call, and user interaction to a clear error-handling strategy.

Step 4: Strategic Report

Use the applicable sections of templates/ceo-report.md for the final report. If the mode is Hold Scope or Scope Reduction, omit expansion proposals and delight items.

  • 10x Version: Include the ambitious version only in an expansion mode.
  • Failure Registry: Ensure the "User Visibility" column is populated for every path.
  • Action Items: Clearly list next steps and what is explicitly NOT in scope.

Important Rules

  • Do not proceed to implementation during this skill. This is a planning-only "fork."
  • Respect scope: Recommend the best approach within the selected mode. Present expansion only when that mode permits it.
  • No Silent Failures: Record missing handling strategies and their likely user impact. Assign severity from evidence, reach, and recoverability. Use critical severity only for demonstrated severe harm. If evidence is missing, name the assumption and the check needed to resolve it.

Source: SKILL.md on GitHub

Skill behaviors

No rule matched.

skilld matched fixed text patterns in SKILL.md and file names. Patterns miss obfuscated code.

skilld run checks every file with the same patterns. It asks for approval before it loads a Skill with a behavior marked Needs approval.

Third-party checks

No third-party reports yet.

Provenance

Signed by skilld at 2a530d0. This ties the file your Agent reads to that commit on GitHub. It does not review the instructions.

Last checked against GitHub 2 days ago.

Activeupdated last month

Capability

context
fork
agent
Plan
effort
high
Other metadata
argument-hint
[feature-name]

README badge

README badge for harlan-zw/harlan-agent-kit/plan-ceo