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 brunob54/superpowers-orchestrator --skill performance-investigationgit clone --depth 1 https://github.com/brunob54/superpowers-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/brunob54/superpowers-orchestrator/performance-investigation)<a href="https://agentmods.dev/skills/brunob54/superpowers-orchestrator/performance-investigation"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/performance-investigation/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/brunob54/superpowers-orchestrator/performance-investigation"><img src="https://agentmods.dev/badge/skills/brunob54/superpowers-orchestrator/performance-investigation.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 | $0.00163 | $0.01793 |
| Opus 5 | $0.00081 | $0.00897 |
| Sonnet 5 | $0.00033 | $0.00359 |
| Haiku 4.5 | $0.00016 | $0.00179 |
Grade A, and why
performance-investigation 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 10d 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 — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Investigation
Measure first. Guess never. Fix once.
Why This Exists
Performance intuition is wrong more often than it's right. Developers consistently misidentify bottlenecks — optimizing the wrong function, caching the wrong query, parallelizing the wrong loop. This skill enforces a measurement-first approach that ensures you fix what's actually slow, not what feels slow.
Phase 1: Baseline
Before changing anything, establish a quantitative baseline.
-
Define the metric. What specifically is slow? Be precise:
- Response time for endpoint X under Y concurrent users
- Time to render component Z with N items
- Memory usage after processing M records
- Build time for the full project
"It's slow" is not a metric. "GET /api/users takes 1200ms p95 with 100 concurrent connections" is.
-
Measure the current state. Run the measurement 3+ times to confirm it's stable and reproducible. For long-running measurements (>2 min each), 2 runs within 5% of each other is sufficient. Record:
- The metric value (with units)
- The measurement method (tool, command, conditions)
- The environment (machine, load, data size)
-
Set a target (if the user hasn't). What would "fast enough" look like? This prevents infinite optimization — you stop when the target is met, not when you run out of ideas.
Baseline: GET /api/users → 1200ms p95 (100 concurrent, 10k users in DB)
Target: < 300ms p95
Method: wrk -t4 -c100 -d30s http://localhost:3000/api/users
Phase 2: Profile
Identify the actual bottleneck — not the guessed one.
- Choose the right profiling tool for the stack. Prefer CLI-based tools that produce text output (Claude can read and analyze these directly). For GUI-only tools, ask the user to run them and share the output.
- Node.js:
node --prof+node --prof-process(text output),clinic doctor --autocannon(generates HTML — ask user to share),0x(flamegraph — ask user to describe hotspots) - Python:
python -m cProfile -s cumulative script.py(text output),py-spy top --pid PID(text output) - Go:
go test -bench . -cpuprofile cpu.prof+go tool pprof -text cpu.prof(text output) - Browser: Ask the user to run Lighthouse CLI (
npx lighthouse URL --output json) or share DevTools Performance tab screenshots - Database:
EXPLAIN ANALYZE(text output — run directly), slow query log - General:
time command,perf stat command(text output)
- Node.js:
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.
- 10d ago First seen · 125 lines · 163 tokens per session scan A ba25aadee547
performance-investigation is a skill published in the GitHub repository brunob54/superpowers-orchestrator (3 stars, last pushed yesterday), licensed MIT. It adds 163 tokens to every session and 1,793 once invoked, about $0.0008 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 skills, from other repositories
verify
Execution verification for CLI/script features — runs commands and captures output for human review. Use after /exec for script changes.
logs
Use when the user wants to check Tandem's activity log, review errors, or debug hook behavior. Also use when the user mentions 'tandem logs', 'what happened', or 'tandem errors'.
release-it
Build production-ready systems with stability patterns: circuit breakers, bulkheads, timeouts, and retry logic. Use when the user mentions "production outage", "circuit breaker", "deployment pipeline", "chaos engineering", "retry storm", "health checks", "my service keeps crashing", "prevent cascading failures", or…
tidewave-integration
Tidewave MCP runtime tools — debugging, smoke testing, live state inspection, SQL queries, hex docs. Use when evaluating code in a running Phoenix app.
debug
Interactive debugging workflow with hypothesis-driven probe loop. Use when: unknown bugs, script errors, silent failures, troubleshooting. Not for: known bugs (use bug-fix), GitHub issue analysis (use issue-analyze), code understanding (use code-explore). Output: debug report with probe journal + root cause + fix.
git-investigate
Git history investigation. Use when: tracking code changes, finding where bugs were introduced, root cause analysis. Not for: code exploration (use code-explore), issue analysis (use issue-analyze). Output: history trace + root cause report.