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/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/byerlikaya/claude-starter-kit/performance"><img src="https://agentmods.dev/badge/skills/byerlikaya/claude-starter-kit/performance.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 | $0.00062 | $0.00559 |
| Opus 5.5 | $0.00025 | $0.00224 |
| Sonnet 5.5 | $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 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 — 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.
- 1mo 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 (24 stars, last pushed 1mo ago), licensed MIT. It adds 62 tokens to every session and 559 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 2026-08-30.
Other skills, from other repositories
oracle
Oracle second-model review: bundle prompts/files, debug, refactor, design.
skill-repair
Diagnose and fix failing or degraded skills automatically - systemic-first triage, per-category playbooks, and a verification plan.
self-improve
Improve the agent itself, or audit its recent performance - better skills, prompts, workflows, and config, plus a quality/reliability/memory-hygiene review of what it did and what failed.
posthog-errors
Weekly cross-project error overview from PostHog - enumerates every project the OAuth grant covers, pulls the last 7 days of error-tracking issues per project, ranks them by impact, flags what's new vs ongoing, and sends one digest with per-project totals, the top issues, and a clickable link to a full committed…
aeon-doctor
Static config-correctness linter for this instance - catches the silent-failure class (unquoted schedules, duplicate keys, unconfigured skills, mode typos, broken requires/MCP refs) that no run-based health skill can see. Notifies only on problems.
manage-skills
A maintenance workflow for checking whether project verification skills still cover the code and rules that changed during a session.