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 skills add Omar-Obando/qwen-orchestrator --skill performancegit clone --depth 1 https://github.com/Omar-Obando/qwen-orchestratorWrote 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/omar-obando/qwen-orchestrator/performance)<a href="https://agentmods.dev/skills/omar-obando/qwen-orchestrator/performance"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/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/skills/omar-obando/qwen-orchestrator/performance"><img src="https://agentmods.dev/badge/skills/omar-obando/qwen-orchestrator/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 | $0.00032 | $0.00946 |
| Opus 5 | $0.00016 | $0.00473 |
| Sonnet 5 | $0.00006 | $0.00189 |
| Haiku 4.5 | $0.00003 | $0.00095 |
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 8d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Skill — Optimization & Profiling
This skill provides systematic performance analysis and optimization guidance.
Performance Budget Template
| Metric | Target | Critical Threshold |
|---|---|---|
| First Contentful Paint | < 1.5s | < 3s |
| Largest Contentful Paint | < 2.5s | < 4s |
| Total Bundle Size | < 200KB gzipped | < 500KB |
| API Response Time (p50) | < 100ms | < 500ms |
| API Response Time (p99) | < 500ms | < 2s |
| Memory Usage | < 100MB | < 500MB |
| CPU Usage (steady) | < 30% | < 80% |
Profiling Methodology
1. Measure First
NEVER optimize without measuring first.
ALWAYS establish a baseline before changes.
ALWAYS compare after optimization with real numbers.
2. Identify Bottleneck
| Layer | Tool | What to Look For |
|---|---|---|
| Frontend | Lighthouse, DevTools | Render blocking, layout thrash |
| Network | Wireshark, Charles | Unnecessary requests, large payloads |
| API | APM tools | Slow endpoints, N+1 queries |
| Database | EXPLAIN, slow query log | Full table scans, missing indexes |
| Compute | CPU profiler | Hot loops, unnecessary computation |
| Memory | Heap snapshot | Leaks, retained objects |
3. Optimize by Category
Algorithmic
- Replace O(n²) with O(n log n) or O(n)
- Use appropriate data structures (Set for lookups, Map for key-value)
- Cache repeated computations (memoization)
- Lazy evaluation for expensive operations
I/O
- Batch database queries
- Use connection pooling
- Implement pagination
- Compress responses (gzip/brotli)
- Use CDN for static assets
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.
- 8d ago First seen · 131 lines · 32 tokens per session scan A d6c173326175
performance is a skill published in the GitHub repository Omar-Obando/qwen-orchestrator (49 stars, last pushed 2mo ago), licensed MIT. It adds 32 tokens to every session and 946 once invoked, about $0.0002 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 2026-09-03.
Other skills, from other repositories
loopx-self-repair
Diagnose and repair LoopX control-plane drift or agent behavior drift. Use when a LoopX task makes unexpectedly small progress, follows a stale or contradictory recommendedaction, ignores a higher-priority blocked item while doing fallback work, reports vague owner/user gates, loses todo projection, misaligns…
code-review
Review diffs and change sets for bugs, regressions, risks, and missing tests.
b3os-ai-code-safety
As code and logic grow, the cost is not the happy path — it is coupling: a change ripples into places you did not touch, and a "small fix" breaks something unrelated. This skill is a code-structure and refactoring guide: structure well from the initial design so a change stays local, apply operational safety where…
tc-doctor
Diagnose and fix tinycode environment issues — Ollama install, model health, tool-call capability, directories, agents, skills, connectivity, and container health.
refire
Turns confirmed findings from a taste into one scoped fix run, then re-verifies each finding at its cited location. Use after /sous-chef:taste when the user says to fix the findings, apply the review, or refire it. Not for new feature work - that is a fresh /sous-chef:fire.
trace
Evidence-driven causal tracing with competing hypotheses, ranked evidence, and discriminating probes.