Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/ivy00johns/skill-madness/perf-loopnpx skills add ivy00johns/Skill-Madness --skill perf-loopgit clone --depth 1 https://github.com/ivy00johns/Skill-MadnessWrote 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.
[](https://agentmods.dev/skills/ivy00johns/skill-madness/perf-loop)<a href="https://agentmods.dev/skills/ivy00johns/skill-madness/perf-loop"><img src="https://agentmods.dev/badge/skills/ivy00johns/skill-madness/perf-loop.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00197 | $0.02695 |
| Opus 5 | $0.00098 | $0.01347 |
| Sonnet 5 | $0.00039 | $0.00539 |
| Haiku 4.5 | $0.00020 | $0.00269 |
Grade A, and why
perf-loop 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 5d 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.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
perf-loop
A configuration of [
loop-controller]. That skill supplies the loop machinery — primitive selection, the full guardrail stack, state externalization. This skill supplies the two things specific to "make it hit the budget": a measured proof under repeatable conditions (a named benchmark artifact, default-FAIL) and the measurement discipline that keeps a noisy benchmark from lying to the loop. Readloop-controllerfor the guardrails; they're inherited, not repeated here.Why
disable-model-invocation: this loop edits and commits code on its own and spends real time re-running benchmarks until a metric is under target. You want to type/perf-loop(or have the orchestrator dispatch it) — not have Claude start an autonomous optimize loop because a number looked slow.
The 5-part contract
| Part | This loop |
|---|---|
| trigger | a metric is over its budget (a slow path, a perf regression, a too-big bundle), or an explicit /perf-loop (optionally scoped to one path/benchmark) |
| action | ONE iteration: benchmark the whole measured set under fixed conditions → identify the single highest-leverage hotspot/regression → optimize one thing → re-benchmark the WHOLE set → re-run the functional suite |
| proof | the metric is under target on EVERY measured path in the benchmark output AND the functional suite still exits 0 — default-FAIL: assume over-budget until the benchmark, run under repeatable conditions, proves otherwise |
| memory | perf_baseline.json (the per-path measured numbers + variance, the durable baseline), PROGRESS.md (hotspot → change → delta log), a git checkpoint per measured improvement |
| stop | metric under target on every path AND suite green OR iteration cap OR no-progress for 3 rounds OR budget cap |
The proof: a measured number under repeatable conditions, default-FAIL
"Fast enough" is not "the profiler looked better" or "the one path I touched sped up." It is every measured path under its target in the benchmark output, re-measured across the whole set, with the functional suite still green — and the benchmark must be reproducible, or the number is noise, not proof. Assume over-budget until you have that artifact. A loop that declares victory off a single fast run on a warm cache ships a regression the next cold start exposes.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 5d ago First seen · 196 lines · 197 tokens per session scan A 3d77f0884d39
perf-loop is a skill published in the GitHub repository ivy00johns/Skill-Madness (11 stars, last pushed 25d ago), licensed MIT. It adds 197 tokens to every session and 2,695 once invoked, about $0.0010 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…