crank
Hands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".
Best use case
crank is best used when you need a repeatable AI agent workflow instead of a one-off prompt.
Hands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".
Teams using crank should expect a more consistent output, faster repeated execution, less prompt rewriting.
When to use this skill
- You want a reusable workflow that can be run more than once with consistent structure.
When not to use this skill
- You only need a quick one-off answer and do not need a reusable workflow.
- You cannot install or maintain the underlying files, dependencies, or repository context.
Installation
Claude Code / Cursor / Codex
Manual Installation
- Download SKILL.md from GitHub
- Place it in
.claude/skills/crank/SKILL.mdinside your project - Restart your AI agent — it will auto-discover the skill
How crank Compares
| Feature / Agent | crank | Standard Approach |
|---|---|---|
| Platform Support | Not specified | Limited / Varies |
| Context Awareness | High | Baseline |
| Installation Complexity | Unknown | N/A |
Frequently Asked Questions
What does this skill do?
Hands-free epic execution for Codex using wave-based sub-agents and lead-side validation. Triggers: "crank", "run epic", "execute epic", "run all tasks", "hands-free execution", "crank it".
Where can I find the source code?
You can find the source code on GitHub using the link provided at the top of the page.
SKILL.md Source
# $crank — Autonomous Epic Execution (Codex Tailoring) This override captures the Codex-native execution model for multi-issue epic work. ## Core Model - The lead agent owns wave planning, validation, and issue state transitions. - Workers are spawned with `spawn_agent(...)`. - Each worker gets a bounded task, explicit owned files, and validation steps. - The lead agent uses `wait_agent(...)` only when integration is blocked on a worker result. ## Codex-Native Wave Loop ### Step 1: Select the wave Use `bd ready --json` when available, or the current plan artifact when beads is unavailable. Only include unblocked work with disjoint file ownership in the same wave. ### Step 2: Prepare worker packets For each issue, include: - issue id and subject - short implementation brief - owned files - validation commands - reminder that the worker is not alone in the repo ### Step 3: Spawn workers Use one `spawn_agent(...)` call per issue with `agent_type="worker"`. ### Step 4: Monitor and correct Collect worker results with `wait_agent(...)`. If a worker needs rework, use `send_input(...)` with a focused correction or launch a new wave for the remaining work. ### Step 5: Validate centrally The lead agent reviews the combined diff, runs repo-level validation, and only then closes issues or advances the wave. ### Step 6: Repeat Continue until all children are closed or the epic is genuinely blocked. ## Constraints 1. Do not rely on batch-spawn, background-report, or timeout-specific wait APIs that are not present in Codex. 2. Do not let workers commit, push, or mutate issue state unless the task explicitly requires it. 3. Serialize overlapping file ownership into later waves instead of risking merge conflicts.
Related Skills
vibe
Comprehensive code validation. Runs complexity analysis then multi-model council. Answer: Is this code ready to ship? Triggers: "vibe", "validate code", "check code", "review code", "code quality", "is this ready".
validation
Full validation phase orchestrator. Vibe + post-mortem + retro + forge. Reviews implementation quality, extracts learnings, feeds the knowledge flywheel. Triggers: "validation", "validate", "validate work", "review and learn", "validation phase", "post-implementation review".
update
Reinstall all AgentOps skills globally from the latest source. Triggers: "update skills", "reinstall skills", "sync skills".
trace
Trace design decisions and concepts through session history, handoffs, and git. Triggers: "trace decision", "how did we decide", "where did this come from", "design provenance", "decision history".
test
Test generation, coverage analysis, and TDD workflow. Triggers: "test", "generate tests", "test coverage", "write tests", "tdd", "add tests", "test strategy", "missing tests", "coverage gaps".
status
Single-screen dashboard showing current work, recent validations, flywheel health, and suggested next action. Triggers: "status", "dashboard", "what am I working on", "where was I".
standards
Language-specific coding standards and validation rules. Provides Python, Go, Rust, TypeScript, Shell, YAML, JSON, and Markdown standards. Auto-loaded by $vibe, $implement, $doc, $bug-hunt, $complexity based on file types.
shared
Shared reference documents for multi-agent skills (not directly invocable)
security
Continuous repository security scanning and release gating. Triggers: "security scan", "security audit", "pre-release security", "run scanners", "check vulnerabilities".
security-suite
Composable security suite for binary and prompt-surface assurance, static analysis, dynamic tracing, repo-native redteam scans, contract capture, baseline drift, and policy gating. Triggers: "binary security", "reverse engineer binary", "black-box binary test", "behavioral trace", "baseline diff", "prompt redteam", "security suite".
scenario
Author and manage holdout scenarios for behavioral validation. Scenarios are stored in .agents/holdout/ where implementing agents cannot see them. Triggers: "$scenario", "holdout", "behavioral scenario", "create scenario", "list scenarios".
scaffold
Project scaffolding, component generation, and boilerplate setup. Triggers: "scaffold", "new project", "init project", "create project", "generate component", "setup project", "starter", "boilerplate".