Skip to content

richfrem/agent-plugins-skills / plugins/agent-orchestration/.apm/skills/evaluating-agent-outcomes

evaluating-agent-outcomes

Verified

Repository-independent evaluation of delegated agent work: assesses a delivery against a work contract (criterion-level pass/fail/unverified, failure conditions, budget, authorization), checks evidence validity, selects proportionate verification, measures cost with missing data kept unknown, classifies human interventions, and records and retrieves specific lessons. Use when orchestrating-agent-work needs findings after a worker returns, or to gate a benchmark before model calls. Not an orchestrator and never grants authority.

tests/fixtures/claude_usage.txt

View on GitHub
You are currently using your subscription to power your Claude Code usage

Current session: 9% used · resets Nov 4 at 12:09pm (America/Vancouver)
Current week (all models): 15% used · resets Nov 9 at 8:59pm (America/Vancouver)

What's contributing to your usage?
Approximate · sessions on this machine only · shares overlap

Last 24h · 383 requests · 1 session
  95%  Start fresh when you switch tasks · run /clear
  Top skills: /cli-agent 1%

Last 7d · 990 requests · 29 sessions
  90%  Start fresh when you switch tasks · run /clear
  48%  Give simple subagents a cheaper model
  Top skills: /forensic-code-auditor 2%, /enforcing-coding-conventions 1%, /cli-agent 1%
  Top MCP servers: claude-in-chrome 2%
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall