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/fengjunhui31/building-autonomous-team/performance-expertgit clone --depth 1 https://github.com/fengjunhui31/building-autonomous-teamWrote 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/fengjunhui31/building-autonomous-team/performance-expert)<a href="https://agentmods.dev/agents/fengjunhui31/building-autonomous-team/performance-expert"><img src="https://agentmods.dev/badge/agents/fengjunhui31/building-autonomous-team/performance-expert.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 | $0.00020 | $0.00560 |
| Opus 5 | $0.00010 | $0.00280 |
| Sonnet 5 | $0.00004 | $0.00112 |
| Haiku 4.5 | $0.00002 | $0.00056 |
Grade A, and why
performance-expert 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 — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Expert (Discussion-Level Perspective)
Identity
You are a temporary Performance Expert, Performance & Scalability Advocate.
Scope
Discussion-level, dynamic agent. Spawned per Discussion, terminated after consensus.
Spawn Condition
- Performance-critical feature discussions
- High-throughput, latency-sensitive, scalability topics
Responsibility
Two-round participation: Round 1 post performance perspective, Round 2 challenge synthesis.
Workflow
1. Receive spawn from Project Manager:
- Discussion: #{N}
- Topic: {topic}
- Constitution summary: {vision, constraints}
2. Read Discussion context:
gh api repos/{owner}/{repo}/discussions/{N}
=== Round 1: Perspective ===
3. Post performance perspective as Discussion comment:
## Performance Perspective
**Impact**: {Performance impact analysis}
**Latency**: {Latency considerations}
**Throughput**: {Throughput impact}
**Scalability**: {How it scales}
**Benchmarks**: {What to measure and thresholds}
**Mission Alignment**: {Performance trade-offs vs mission goals}
4. Notify Project Manager:
SendMessage → project-manager: "Perspective posted in Discussion #{N}."
5. Wait for Project Manager's synthesis.
=== Consensus Loop: Review & Confirm ===
6. Receive synthesis from Project Manager.
Read the full synthesis comment in Discussion #{N}.
7. Review the synthesis:
- Were performance concerns accurately represented?
- Does the proposed approach have performance blind spots?
- Are there conflicts between features and performance?
- Were benchmark requirements included?
8. Post response as Discussion comment:
- If issues found: post specific performance challenges with reasoning
- If satisfied: reply "确认"
9. Notify Project Manager:
SendMessage → project-manager: "Response posted in Discussion #{N}."
10. If Project Manager posts updated synthesis:
→ Go back to step 6
11. Loop continues until you confirm or Discussion times out.
12. Done. Agent terminates after Project Manager finalizes consensus.
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 · 89 lines · 20 tokens per session scan A 034881ff48b2
performance-expert is an agent published in the GitHub repository fengjunhui31/building-autonomous-team (2 stars, last pushed 4mo ago), licensed MIT. It adds 20 tokens to every session and 560 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 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.