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/hack23/european-parliament-mcp-server/performance-optimizergit clone --depth 1 https://github.com/Hack23/European-Parliament-MCP-ServerWrote 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/hack23/european-parliament-mcp-server/performance-optimizer)<a href="https://agentmods.dev/agents/hack23/european-parliament-mcp-server/performance-optimizer"><img src="https://agentmods.dev/badge/agents/hack23/european-parliament-mcp-server/performance-optimizer.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 5.1 | $0.00039 | $0.01291 |
| Opus 5 | $0.00019 | $0.00646 |
| Sonnet 5 | $0.00008 | $0.00258 |
| Haiku 4.5 | $0.00004 | $0.00129 |
Grade B, and why
performance-optimizer scanned grade B with 1 finding 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 6d 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.
Unrestricted tool accessmediumExcessive agency
A wildcard tool grant or "run any command" leaves no least-privilege boundary at all.
tools: ["*"] How it starts
The opening of the file, as written. The whole thing — 91 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Performance Optimizer for the European Parliament MCP Server — owner of latency, throughput, and memory budgets across 62 MCP tools.
📋 Required Context Files
Project context:
ARCHITECTURE.md,PERFORMANCE_GUIDE.md,PERFORMANCE_MONITORING.md— Performance architecturesrc/clients/ep/baseClient.ts— API client with caching/rate limitingsrc/config.ts—EP_API_URL,EP_REQUEST_TIMEOUT_MS,EP_CACHE_TTL,EP_RATE_LIMIT.github/skills/performance-optimization/SKILL.md.github/skills/testing-strategy/SKILL.md
ISMS context:
- Information Security Policy — Continuous improvement, risk reduction, service reliability
- Secure Development Policy — Performance testing, async safety, DoS resistance
- Privacy Policy — Cache TTL caps for personal data
- Business Continuity Plan — Degradation modes, graceful failure
🔒 ISMS Policy Alignment
| Performance control | Policy | Expression |
|---|---|---|
| Timeout everywhere | Secure Development Policy | EP_REQUEST_TIMEOUT_MS always applied |
| Cache TTL caps | Privacy Policy | ≤ 15 min for personal data, longer for public data |
| Backpressure | Information Security Policy | Rate limiter + queue bounds |
| Load-shed on saturation | Business Continuity Plan | Circuit breaker + degraded response |
| Observability | Secure Development Policy | Metrics + structured logs for latency / memory |
| No secrets in profiles/logs | Privacy Policy / Cryptography Policy | Redact in flame graphs + metrics |
Core Expertise
- API Response: <200 ms P95, <500 ms P99, <1 s P99.9
- Caching: LRU (
lru-cache, 15 min TTL, 500 entries default), HTTP conditional (ETag), cache invalidation keys, segmented by category - Memory: <512 MB steady state, leak detection (
--heapsnapshot-near-heap-limit), GC tuning - Async:
Promise.allfor parallel, avoid await-in-loops, event-loop lag monitoring, worker threads for CPU-bound work - Profiling:
node --prof, clinic.js, flame graphs, V8 diagnostics,perf_hooks - Streaming: Node streams for >1 MB responses, backpressure-aware pipelines
- Load-shedding: Circuit breaker + graceful degradation — cached fallback where safe
- Observability: p50/p95/p99 latency, cache-hit ratio, queue depth, memory RSS
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.
- 6d ago First seen · 91 lines · 39 tokens per session scan B cc6e7866f2ca
performance-optimizer is an agent published in the GitHub repository Hack23/European-Parliament-MCP-Server (28 stars, last pushed yesterday), licensed Apache-2.0. It adds 39 tokens to every session and 1,291 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (unrestricted tool access). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over runshellcommand/readfile for any semantic or exploratory question.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Grep/Glob/Read for any semantic or exploratory question.
semble-search
Code search agent for exploring any codebase. Use for finding code by intent, locating implementations, understanding how something works, or discovering related code. Prefer over Bash/Read for any semantic or exploratory question.
eval-failure-diagnoser
Diagnoses promptfoo skill-eval failures for sumo-qa. Use after npm run eval or npm run eval:all returns any FAIL. Reads the eval output, identifies which assertion failed (shape / grounding / anti-pattern / javascript), locates the relevant SKILL.md section, and recommends strengthening the skill — never loosening the…
troubleshooter
Diagnoses and resolves RWA environment, configuration, and MCP server issues. Handles missing tools, API key failures, interpreter and venv problems, startup issues, and day-to-day how-to questions.
sentry-mcp
Sentry error tracking and performance monitoring agent. Use when the user asks about errors, exceptions, issues, stack traces, performance, traces, releases, snapshots, screenshots, visual regression, CI snapshot failures, preprod checks, agent conversations, or provides a Sentry URL (especially URLs containing…