OpenSkillIndex← back to search
claude-code

Agentsys perf-theory-tester

Use when running controlled perf experiments to validate hypotheses.

install
source · Clone the upstream repo
git clone https://github.com/agent-sh/agentsys
Claude Code · Install into ~/.claude/skills/
T=$(mktemp -d) && git clone --depth=1 https://github.com/agent-sh/agentsys "$T" && mkdir -p ~/.claude/skills && cp -r "$T/.kiro/skills/perf-theory-tester" ~/.claude/skills/agent-sh-agentsys-perf-theory-tester && rm -rf "$T"
manifest: .kiro/skills/perf-theory-tester/SKILL.md
source content

perf-theory-tester

Test hypotheses using controlled experiments.

Follow 

docs/perf-requirements.md
as the canonical contract.

Required Steps

  1. Confirm baseline is clean.
  2. Apply a single change tied to the hypothesis.
  3. Run 2+ validation passes.
  4. Revert to baseline before the next experiment.

Output Format

hypothesis: <id>
change: <summary>
delta: <metrics>
verdict: accept|reject|inconclusive
evidence:
  - command: <benchmark command>
  - files: <changed files>

Constraints

  • One change per experiment.
  • No parallel benchmarks.
  • Record evidence for each run.