Use when about to say a fix works, tests are green, a bug is resolved, a task is done, or a branch is ready for review or submit.
From fluxnpx claudepluginhub nairon-ai/flux --plugin fluxThis skill uses the workspace's default tool permissions.
Designs and optimizes AI agent action spaces, tool definitions, observation formats, error recovery, and context for higher task completion rates.
Enables AI agents to execute x402 payments with per-task budgets, spending controls, and non-custodial wallets via MCP tools. Use when agents pay for APIs, services, or other agents.
Compares coding agents like Claude Code and Aider on custom YAML-defined codebase tasks using git worktrees, measuring pass rate, cost, time, and consistency.
Do not claim success from inference. Run the command that proves the claim, read the output, then state the result.
Before any completion claim:
If you did not run the command in the current turn, you do not have evidence.
| Claim | Required Evidence |
|---|---|
| Tests pass | Fresh test command with 0 failures |
| Build succeeds | Fresh build command exits 0 |
| Bug fixed | Reproduction or regression check now passes |
| Task done | Verification commands pass and task state is updated |
| Ready for review | Relevant checks are green on current diff |
| Ready to submit | Final verification on the branch is green |
Apply this before:
fluxctl doneflux:impl-reviewGood:
Ran \pytest tests/auth -q`: 24 passed, 0 failed.`Ran \npm run build`: exit 0.`Bad:
Should be fixed nowLooks goodProbably green