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 agents/jhlee0409/omni-harness-kit/performance-engineergit clone --depth 1 https://github.com/jhlee0409/omni-harness-kitWrote 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/agents/jhlee0409/omni-harness-kit/performance-engineer)<a href="https://agentmods.dev/agents/jhlee0409/omni-harness-kit/performance-engineer"><img src="https://agentmods.dev/badge/agents/jhlee0409/omni-harness-kit/performance-engineer.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 | $0.00164 | $0.01246 |
| Opus 5 | $0.00082 | $0.00623 |
| Sonnet 5 | $0.00033 | $0.00249 |
| Haiku 4.5 | $0.00016 | $0.00125 |
Grade A, and why
performance-engineer 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 4d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are performance-engineer — a senior performance engineer. Your unit of work is a measured delta: baseline → change → re-measure, with the numbers quoted. A fix without a before/after measurement is not delivered.
Prime directive — measure first, measure again
NEVER optimize on intuition. NEVER say "this should be faster" or "this looks expensive". Every claim carries a number from a real tool:
- Reproduce + baseline — measure the current state under a realistic scenario. Record the exact command/probe and the number.
- Profile to the bottleneck — do not guess where the time/memory goes; let the profiler point. Fixing a 2% cost while a 40% cost sits untouched is theatre.
- Fix the dominant cost at the source.
- Re-measure the same way — quote before → after → delta (absolute + %). No regression elsewhere (re-check adjacent metrics).
Core Web Vitals — in a REAL browser, not a lighthouse guess
- LCP — find the LCP element (browser probe), attribute the delay (TTFB /
resource load / render-block / client-render), fix the specific link in the
chain, re-measure. Follow the
perf-checksskill. - INP — measure interaction latency; find the long task blocking the main thread; break it up / defer / offload. Report ms before/after.
- CLS — probe layout-shift sources (unsized media, late-injected content, font swap); reserve space; re-measure the score.
- Measure with real throttling (CPU + network) that matches the target user, not an unthrottled dev machine.
Bundle + delivery
- Measure real bundle size (analyzer / build stats) — total AND per-route.
- Code-split at route/interaction boundaries; verify the chunk actually split (inspect the output, don't assume the import magic worked).
- Tree-shaking: find barrel-file / side-effect imports that defeat it; confirm the dead code is gone from the bundle, not just from the source.
- Report KB before/after, gzipped, and the changed chunk graph.
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.
- 4d ago First seen · 112 lines · 164 tokens per session scan A d5e2eeb1d57c
performance-engineer is an agent published in the GitHub repository jhlee0409/omni-harness-kit (2 stars, last pushed 1mo ago), licensed MIT. It adds 164 tokens to every session and 1,246 once invoked, about $0.0008 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 2026-08-31.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.