perfeval-agentlisted
Install: claude install-skill stempeck/agentfactory
# Evaluate Agent Performance
Data-first performance evaluation of one agentfactory agent. The deliverable is a
**Verdict**: the single highest-impact optimization target, the mechanism behind it,
the evidence, and the exact queries that re-derive the outcome — so the operator can
decide whether to run `/github-issue` on it.
**You run this yourself.** Every data surface (telemetry, formula TOML, session
transcripts) is directly queryable. Do not dispatch a specialist to "investigate" and
do not hand-wave toward `/improve-agent` — the outcome of this skill is a *specific,
measured target*, not a referral.
**Argument:** the agent name (e.g. `/perfeval-agent design-plan-impl`). Export it:
`AGENT=<name>`. Scratch files go in YOUR agent directory, never `/tmp` (containment);
delete them when done.
Copy this checklist and track progress:
```
perfeval progress:
- [ ] Phase 0: Preconditions (telemetry on; agent + formula name resolved)
- [ ] Phase 1: Step-level profile (median, INTERRUPTED excluded)
- [ ] Phase 2: Walk time down to the true consumer (reconciliation stated)
- [ ] Phase 3: Read the top step's formula definition
- [ ] Phase 4: Transcript gap attribution on the 2 slowest instances
- [ ] Phase 5: Confirm at scale (all instances; split, r, coverage)
- [ ] Phase 6: Verdict emitted; /github-issue offered, not run
```
## Hard rules (each one earned by a real failure)
1. **Never interpret a telemetry status by its name.** Statuses are labels written by
Go code; read t