← ClaudeAtlas

krypton-executionlisted

Use when executing an approved Krypton plan, GOAL.md, or implementation plan that already defines intent, ownership, contract, cutover, task boundaries, and acceptance evidence. Use for main-agent execution with explorer, plan-reviewer, reviewer, maintainer, or verifier gates.
jturntdev/krypton · ★ 0 · AI & Automation · score 68
Install: claude install-skill jturntdev/krypton
# Krypton Execution Krypton Execution runs an approved plan without drifting from its ownership, cutover, and evidence contract. ## Required Roles Use the role expectations in `../../docs/required-roles.md` when the harness supports named agents. Implementation stays with the main agent. The normal execution stack is: ```text explorer -> main agent -> plan-reviewer -> reviewer -> maintainer -> verifier ``` Use the individual prompt templates in this skill folder: - `post-plan-reviewer-prompt.md` - `reviewer-prompt.md` - `maintainer-prompt.md` ## Entry Rule Do not invent the plan inside this workflow. If no approved plan, goal document, or clear task board exists, ask for one direct input or use Krypton Planning first. Before work starts, restate: ```text Goal: Plan path: Intent: Truth owner: Contract boundary: Cutover: Displaced path: Acceptance evidence: Kill criteria: Forbidden moves: ``` ## Task Board Turn the plan into an ordered board: ```text Task: Owner: Input: Files allowed: Files forbidden: Output: Evidence: Depends on: Parallel safe: ``` Run implementation tasks sequentially in the main agent unless the approved plan explicitly says otherwise. ## Execution Loop For each task: 1. Confirm the task still matches the plan contract. 2. Gather only the context needed for the task. 3. Implement directly in the main agent. 4. Review the result before integration or checkpoint. 5. Check for wrong owner, duplicate path, missing cutover, contract drift, and we