agentsys: Skill for Claude Code

.kiro/skills/perf-theory-tester/SKILL.md

perf-theory-tester is a skill for Claude Code, Kiro from agent-sh/agentsys. It costs 16 tokens per session (177 once invoked), scanned A, original, MIT.

A method for testing performance ideas through controlled experiments, changing one thing at a time and comparing results with a clean baseline.

In plain words
What is it for?
It helps benchmark a proposed optimization, run repeated validation passes, record metrics and evidence, and decide whether the change should be kept.
Why use it?
It makes performance conclusions easier to trust by separating the effect of one change from unrelated changes or noisy measurements.

Skill for Claude CodeKiro

Written for Claude Code and Kiro: shipped in a Claude Code plugin, but also installed under .kiro/.

This is agent-sh/agentsys's own configuration. It tells Claude Code and Kiro how to work on agentsys itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentsys configures →

Part of the agentsys plugin — 28 skills, 1 hook shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to agent-sh/agentsys. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/agent-sh/agentsys/main/.kiro/skills/perf-theory-tester/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/agent-sh/agentsys

Made for: Claude Code, Kiro.

Or install agentsys, the plugin that ships this one along with the rest of its 28 skills, 1 hook.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for perf-theory-tester

README.md
[![agentmods](https://agentmods.dev/badge/skills/agent-sh/agentsys/perf-theory-tester/github.svg)](https://agentmods.dev/skills/agent-sh/agentsys/perf-theory-tester)
Your own site
<a href="https://agentmods.dev/skills/agent-sh/agentsys/perf-theory-tester"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/perf-theory-tester/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for perf-theory-tester

Your own site · 80×15
<a href="https://agentmods.dev/skills/agent-sh/agentsys/perf-theory-tester"><img src="https://agentmods.dev/badge/skills/agent-sh/agentsys/perf-theory-tester.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 16 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 177 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00016 $0.00177
Opus 5 $0.00008 $0.00088
Sonnet 5 $0.00003 $0.00035
Haiku 4.5 $0.00002 $0.00018

Measured 10d ago against content hash 091ffb327ed6, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

perf-theory-tester scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.kiro/skills/perf-theory-tester/SKILL.md · 37 lines

What it actually says

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.
Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 10d ago First seen · 37 lines · 16 tokens per session scan A 091ffb327ed6

Subscribe to this mod's changes

perf-theory-tester is a skill published in the GitHub repository agent-sh/agentsys (984 stars, last pushed 3d ago), licensed MIT. It adds 16 tokens to every session and 177 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

remove-ai-slops

Removes AI-generated code smells from branch changes or an explicit file list behind regression tests. Use when the user asks to clean up, deslop, or remove AI-slop patterns from recent changes.

code-yeongyu/oh-my-openagent · 45 tokens

verify-implementation

A workflow that runs a project’s verification skills to produce a report on coding patterns, architecture rules, and project conventions. It is intended for work after implementation, before a pull request, or during code review.

sangrokjung/claude-forge · 37 tokens

refactor

Guides a refactor, cleanup, or restructure with the right decomposition. Use when the user asks to refactor, simplify, extract, or modernize code.

code-yeongyu/oh-my-openagent · 36 tokens

visual-qa

Runs rigorous visual QA across web, terminal, and paginated surfaces with screenshot evidence and a verdict. Use for any UI build or change, or when asked whether a page, component, or TUI looks right.

code-yeongyu/oh-my-openagent · 47 tokens

pre-publish-review

Nuclear-grade 12-agent pre-publish release gate. Runs /get-unpublished-changes to detect all changes since last npm release, spawns up to 10 ultrabrain agents for deep per-change analysis, invokes /review-work (orchestrator manual QA plus one gate reviewer) for holistic review, and 1 oracle for overall release…

code-yeongyu/oh-my-openagent · 161 tokens

work-with-pr

Full PR lifecycle in a fresh task-owned git worktree: implement via the ulw-loop skill with mandatory evidence-bound manual QA → reviewer-readable English PR → verification loop (CI + Cubic, where Cubic is skipped only when its quota is exhausted) → merge by default → worktree cleanup. Decomposes one task into the…

code-yeongyu/oh-my-openagent · 211 tokens