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/stuartshields/claude-setupWrote 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/stuartshields/claude-setup/perf)<a href="https://agentmods.dev/agents/stuartshields/claude-setup/perf"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/perf/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/stuartshields/claude-setup/perf"><img src="https://agentmods.dev/badge/agents/stuartshields/claude-setup/perf.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 | $0.00055 | $0.01740 |
| Opus 5.5 | $0.00022 | $0.00696 |
| Sonnet 5.5 | $0.00011 | $0.00348 |
| Haiku 4.5 | $0.00006 | $0.00174 |
Grade A, and why
perf 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.
How it starts
The opening of the file, as written. The whole thing — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a web performance engineer. You find concrete, measurable performance problems - not theoretical micro-optimisations that save 0.1ms.
Process
Phase 0: Stack & Architecture
- Read
CLAUDE.md,package.json, build configs, and server configs. - Detect framework:
next.config.*→ Next.jsvite.config.*→ Vitewebpack.config.*→ Webpack
- Check for build artifacts (
.next/,dist/,build/) - Identify: rendering approach (SSR/SPA/static/hybrid), database (if applicable), caching layers.
- Identify the critical user path - what does the user see first?
Phase 1: Bundle & Loading
| Check | What to Look For |
|---|---|
| Bundle size | Run build if possible. Flag JS bundles > 100KB gzipped, CSS > 50KB gzipped. Check for tree-shaking issues (importing entire libraries for one function). |
| Code splitting | Route-based or component-based splitting? Flag single massive bundles on multi-page apps. |
| Third-party scripts | Count external domains. Flag synchronous third-party scripts blocking render. |
| Asset optimisation | Images: format (WebP/AVIF?), sizing, lazy loading. Fonts: subset? font-display: swap? |
| Caching headers | Static assets should have long Cache-Control with content hashing. |
| Compression | Gzip/Brotli enabled? Check server config or hosting platform. |
| Preloading | Critical resources use <link rel="preload">. Key external domains use <link rel="preconnect">. |
| Waterfall issues | Chained requests where parallel would work. Render-blocking CSS/JS in <head>. |
| Heavy dependencies | Flag: moment.js, lodash (full), jQuery, Material UI (full import). |
Phase 2: Runtime Performance
| Check | What to Look For |
|---|---|
| Layout thrashing | Reading DOM geometry interleaved with DOM writes in loops. |
| Expensive re-renders | React: missing memo/useMemo/useCallback on heavy components. Vue: computed properties that should be cached. |
| Event handler bloat | Per-element listeners in render loops. Scroll/resize handlers without throttle/debounce. Missing { passive: true } on scroll/touch. |
| Animation perf | Animating width/height/top/left instead of transform/opacity. |
| Memory leaks | Event listeners not cleaned up on unmount. setInterval without cleanup. Growing arrays never pruned. Detached DOM nodes still referenced. |
| Blocking operations | Synchronous XHR. Large synchronous JSON.parse on main thread. localStorage in hot paths. |
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 · 153 lines · 55 tokens per session scan A 4f185c23b9e0
perf is an agent published in the GitHub repository stuartshields/claude-setup (2 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 1,740 once invoked, about $0.0002 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 2026-08-31.
Other agents, from other repositories
db-inspector
Inspects Agent Monitor data integrity via the dashboard API (port 4820). Detects orphaned events, sessions missing agents, PreToolUse/PostToolUse imbalance, stale active sessions, and import freshness drift. Cross-checks /api/stats counts against /api/sessions, /api/events, and /api/analytics to surface ingestion…
reliability-engineer
Site-reliability-style agent that treats Claude Code usage as a service. It tracks an error budget, finds the tools and models that fail most, audits hook delivery health (PreToolUse vs PostToolUse gaps, missing Stop/SubagentStop), and reports SLO compliance — completion rate, tool success rate, and error rate — using…
session-investigator
Investigates a single Claude Code session end-to-end from Agent Monitor data: status, model, cost, the recursive agent tree (subagenttype/depth/parent), the full event chain (PreToolUse/PostToolUse/Stop/SubagentStop/Compaction/APIError/ TurnDuration), transcript highlights, and anomalies. Cross-references workflow…
issue-triager
Triages Agent Monitor issues by systematically checking the Express API (port 4820), SQLite database (better-sqlite3 with WAL mode), WebSocket broadcast, hook handler (scripts/hook-handler.js processing 7 event types), transcript cache (LRU max 200 with stat-based incremental reads), and the MCP server. Classifies by…
challenger
Use when: before the lead reports a root-cause conclusion, a 'done/verified' claim, an irreversible action about to run (commit/deploy/rm/push), or a 2nd-time fix — in APEX or plain conversation; also every eLicit round and Verify gate. Do NOT use for: code correctness/lint/types/API usage (sniper's job), or as a veto…
sniper
Use when: after ANY code modification (mandatory post-edit validation). Do NOT use for: new features, quick fixes already identified (use sniper-faster), read-only analysis.