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 byerlikaya/claude-starter-kit --skill performancegit clone --depth 1 https://github.com/byerlikaya/claude-starter-kitWrote 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/byerlikaya/claude-starter-kit/performance)<a href="https://agentmods.dev/skills/byerlikaya/claude-starter-kit/performance"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/performance.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 | $0.00062 | $0.00559 |
| Opus 5 | $0.00031 | $0.00280 |
| Sonnet 5 | $0.00012 | $0.00112 |
| Haiku 4.5 | $0.00006 | $0.00056 |
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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance
Trigger phrases: "performance", "slow", "optimization", "profiling", "N+1", "latency", "memory leak", "leaked memory", "load test", "seconds to open", "seconds to respond", "anything slower", "make it slower"
Core rule: measure first, optimize later. Optimization without measurement is a guess; it usually speeds up the wrong place and adds complexity. Stack-agnostic; do a web search when you need the profiling tool/library.
Method (in order)
- Set a target — what is "acceptable"? (p95 latency, throughput, memory ceiling). Numeric.
- Measure — find the real bottleneck with a profiler/APM/benchmark; don't start from a guess.
- Fix the single most expensive thing — Amdahl: speeding up a 5% path by 2x is wasted; target the hot path.
- Measure again — did it actually improve, is there a regression.
- Stop — once you hit the target, finish; no endless micro-optimization.
Common bottlenecks
Catalog of common bottlenecks + fixes to consult: references/bottlenecks.md.
Measurement tips
- Measure under load (a single request misleads); with a realistic data volume.
- Not p50, but p95/p99 — tail latency is what burns the user.
- Don't trust micro-benchmarks; an end-to-end profile is more honest.
Invariant rules
- Don't optimize without measuring — a change without a profile = a guess.
- Target the hot path — don't speed up the small share.
- Don't break correctness — don't sacrifice behavior/edge cases for speed.
- Complexity budget — make an optimization that seriously hurts readability only if there is a measured gain; comment it.
- Stop once you hit the target — YAGNI; no premature/excessive optimization.
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 · 41 lines · 62 tokens per session scan A 41ab8fe6f5e2
performance is a skill published in the GitHub repository byerlikaya/claude-starter-kit (22 stars, last pushed yesterday), licensed MIT. It adds 62 tokens to every session and 559 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.
systematic-debugging
Structured debugging methodology — use before proposing fixes for any error or failure. Covers: code bugs, build errors, deploy failures, config conflicts, dependency issues, infra problems. Also use when previous fix attempts failed or root cause is unclear.
review-loop
Run the adversarial verification loop — implement, then hand the change to a fresh checker that did not write it, fix what it finds, and re-dispatch until APPROVE. Use before claiming any behavioural change is done, and on requests like "review loop", "adversarial review", "independent review", "get this verified"…
debug-systematic
Systematic 4-phase debugging methodology for complex, intermittent, or mysterious issues. Use when investigating bugs, race conditions, or unexplained failures.
debugging-strategies
Master systematic debugging techniques, profiling tools, and root cause analysis to efficiently track down bugs across any codebase or technology stack. Use when investigating bugs, performance issues, or unexpected behavior.
diagnose
Disciplined diagnosis loop for hard bugs and performance regressions. Reproduce → minimise → hypothesise → instrument → fix → regression-test. Use when user says "diagnose this" / "debug this", reports a bug, says something is broken/throwing/failing, or describes a performance regression.