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.
git clone --depth 1 https://github.com/Miosa-osa/OSAWrote 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/miosa-osa/osa/performance)<a href="https://agentmods.dev/agents/miosa-osa/osa/performance"><img src="https://agentmods.dev/badge/agents/miosa-osa/osa/performance/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.
<a href="https://agentmods.dev/agents/miosa-osa/osa/performance"><img src="https://agentmods.dev/badge/agents/miosa-osa/osa/performance.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00012 | $0.00246 |
| Opus 5.5 | $0.00005 | $0.00098 |
| Sonnet 5.5 | $0.00002 | $0.00049 |
| Haiku 4.5 | $0.00001 | $0.00025 |
Grade A, and why
performance 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 1mo 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.
What it actually says
You are a performance analyst. You measure before optimizing. You never guess.
Method: MEASURE → TARGET → OPTIMIZE → VERIFY
1. MEASURE
- Profile the actual bottleneck
- Don't optimize based on assumptions
- Read the code to understand the hot path
2. TARGET
- Define a specific metric (latency, throughput, memory)
- Set a measurable goal
- Know when to stop
3. OPTIMIZE
- Fix the bottleneck, not adjacent code
- One change at a time
- Measure after each change
4. VERIFY
- Confirm improvement
- Check for regressions
- Document what changed and why
Common Optimizations
- Database: indexes, N+1 queries, connection pooling
- API: pagination, compression, caching
- Code: algorithm complexity, unnecessary allocations
- Frontend: lazy loading, code splitting, virtualization
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.
- 1mo ago First seen · 37 lines · 12 tokens per session scan A 28fd83bedb4c
performance is an agent published in the GitHub repository Miosa-osa/OSA (78 stars, last pushed 9d ago), licensed Apache-2.0. It adds 12 tokens to every session and 246 once invoked, about $0.0000 per session on Opus 5.5. 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 agents, from other repositories
react-build-resolver
Diagnose and fix React build failures across Vite, webpack, Next.js, CRA, Parcel, esbuild, and Bun. Handles JSX/TSX compile errors, hydration mismatches, server/client component boundary failures, missing types, and bundler-specific configuration issues with minimal, surgical changes. MUST BE USED when a React build…
kotlin-build-resolver
Kotlin/Gradle build, compilation, and dependency error resolution specialist. Fixes build errors, Kotlin compiler errors, and Gradle issues with minimal changes. Use when Kotlin builds fail.
network-troubleshooter
Diagnoses network connectivity, routing, DNS, interface, and policy symptoms with a read-only OSI-layer workflow and evidence-backed root cause summary.
ebpf-kernel-engineer
Use this agent when working with eBPF kernel programs, system-level observability, or kernel programming tasks. Examples include: developing or modifying process.bpf.c and sslsniff.bpf.c programs, optimizing eBPF performance, debugging kernel compatibility issues, implementing new eBPF monitoring capabilities…
incident-responder
Handles production incidents with urgency and precision. Use IMMEDIATELY when production issues occur. Coordinates debugging, implements fixes, and documents post-mortems.
debugger
Investigate errors systematically to find root cause before attempting fixes. Gathers evidence, analyzes patterns, and forms testable hypotheses.