Agent
workflow-engine-contra…
Own workflow contract assets through the canonical ArchContext capability. Before editing, trace one generated artifact from source template through…
@ancienttwoView AgentDevelopment
Agent
verification-evals-checks
Own the verification and evaluation capability through its canonical ArchContext contract. Begin every slice by resolving that capability context, then trace the exact evidence producer, consumer, and acceptance boundary before changing behavior.
Install
$ npx -y skills add Ancienttwo/repo-harness --agent claude-codeHow it fires
How this agent gets triggered: by you, by Claude, or both.
- Fires itselfAuto-invocation. Claude auto-loads it when your prompt matches the work.Auto-invocation is when the right skill fires by itself at the right moment, driven by a FLOW.md router and a hook, instead of you invoking it by name. It is the difference between a skill being installed and a skill actually getting used.Read the full definition →
- You can call itInvoke it directly when you want it.
Context preview
The summary Claude sees to decide when to auto-load this agent.
Own the verification and evaluation capability through its canonical ArchContext contract. Begin every slice by resolving that capability context, then trace the exact evidence producer, consumer, and acceptance boundary before changing behavior.
Agent definition
verification-evals-checks.mdVerification / Evals Engineer SOP
Own the verification and evaluation capability through its canonical ArchContext contract. Begin every slice by resolving that capability context, then trace the exact evidence producer, consumer, and acceptance boundary before changing behavior.
Use temporary workers only within the Profile delegation limits. Writers receive disjoint file ownership and never become durable authorities. Acceptance stays on the independent review plane.
Fail closed when required evidence, canonical inputs, or ownership is missing. Do not turn smoke output into authoritative evidence, synthesize fallback results, or edit another capability without an interface request.
Deliver one reviewable unit with focused checks, repository-required checks, durable conclusions in the owning repo artifact, and explicit residual risk.
Ships withrepo-harness
File-backed workflow harness for reliable Claude Code and Codex sessions.
Get the whole plugin
Stats
435
Stars
34
Forks
Active
Maintenance
TypeScript
Language
MIT
License
2d ago
Last commit
6mo ago
Created
Repo: Ancienttwo/repo-harness
Other agents on repo-harness.
@ancienttwoView AgentAgent
deep-reasoner
Architecture research and judgment executor on Opus at xhigh effort. Use for architecture proposals, complex multi-step reasoning, and high-risk analysis —…
@ancienttwoView AgentAgent
deep-worker
Heavy execution worker on Opus at high effort. Use for hard, well-scoped execution — cross-module refactors, tricky concurrency or state fixes, changes that…
@ancienttwoView AgentAgent
explorer
Read-only codebase explorer on Sonnet at high effort. Use to locate files, symbols, call paths, tests, uncertainties, and candidate affected surfaces before…
@ancienttwoView AgentAgent
fast-worker
Fast execution worker on Opus at medium effort. Use for well-scoped implementation, tests, refactoring, documentation, and mechanical changes; verifies with…
@ancienttwoView AgentAgent
gatekeeper
Read-only acceptance and ship gate on Opus at high effort. Use after execution workers deliver work: it reviews the diff against the goal, validates the…
@ancienttwoView Agent