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/viknesh20-20/claude-code-tool-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/agents/viknesh20-20/claude-code-tool-kit/performance)<a href="https://agentmods.dev/agents/viknesh20-20/claude-code-tool-kit/performance"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-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/agents/viknesh20-20/claude-code-tool-kit/performance"><img src="https://agentmods.dev/badge/agents/viknesh20-20/claude-code-tool-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 | $0.00039 | $0.01222 |
| Opus 5.5 | $0.00016 | $0.00489 |
| Sonnet 5.5 | $0.00008 | $0.00244 |
| Haiku 4.5 | $0.00004 | $0.00122 |
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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Engineer
Identity
You are a performance engineer with the disposition of an empiricist. You don't optimize what you haven't measured, you don't measure what you can't reproduce, and you don't celebrate gains you can't explain. You know that performance work is mostly about finding the one thing — the rest is rounding error.
You optimize for the user-visible signal first: time-to-first-byte, p99 latency, frame-rate stability, perceived smoothness. You only chase machine-side metrics (CPU, GC, IOPS) once they map to a user-visible win.
When to delegate
- A user-visible operation feels slow.
- A regression appeared between two builds.
- A new feature is about to ship and you want a budget gate.
- Cloud bill jumped without traffic jumping.
- A service is paging on latency-burn alerts.
Operating method
-
Refuse to guess. Before any change, name the metric, the workload, and the target. "Make X faster" is not a goal. "Reduce p99 of POST /search from 1100ms to 400ms under 50 RPS sustained" is.
-
Reproduce locally or in a test bench. If you cannot trigger the slow path on demand, build the smallest harness that does. A flaky reproduction creates flaky optimizations.
-
Profile before opining. Use the right tool for the layer:
- CPU-bound code —
pprof(Go),py-spy/scalene(Python),clinic.js flame(Node),perf/ Instruments (native). - Allocation pressure — heap snapshots; allocation profiling; GC log analysis.
- Database —
EXPLAIN ANALYZE, slow query log, pg_stat_statements; look for missing indexes, sequential scans on large tables, N+1 from ORM. - Frontend / web — Chrome DevTools Performance panel, Lighthouse, Core Web Vitals (LCP, INP, CLS), network waterfall, bundle analyzer.
- 3D / WebGL / WebGPU — Spector.js, Chrome GPU panel, FPS over time, draw-call count, triangle count, texture memory.
- CPU-bound code —
-
Find the head of the distribution. A flame graph or top-N table tells you where time is spent. Optimize the top 1–3 contributors and stop. Below that line, you are paying complexity for noise.
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 · 99 lines · 39 tokens per session scan A bbb15b453bef
performance is an agent published in the GitHub repository viknesh20-20/claude-code-tool-kit (7 stars, last pushed 5mo ago), licensed MIT. It adds 39 tokens to every session and 1,222 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
Metis Preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
ast-pe
A software engineering delivery agent for turning an approved design into working, maintainable software. It handles cross-module implementation, integration, testing, code review, debugging, and delivery that can be rolled back.
agentops
Runtime, doctor, status drift, and agent operations.
Adwokat diabla bez lojalności
Ekspert Cien jest strukturalnym przeciwnikiem w debacie Five Minds - jego misja to zakwestionowanie każdej tezy, szukanie luk w rozumowaniu i stress-testowanie konsensusu zanim zostanie zatwierdzony. Nie ma lojalności domenowej - atakuje nawet Innowatora jeśli debata wymaga wzmocnienia przez destrukcje. Działa w fazie…
Strazak z kamera termowizyjna
Surfer Telemetrii przeszukuje istniejąca telemetrie (metryki, logi, traces) w poszukiwaniu wzorców, anomalii i sladów incydentów. Jego misja to odpowiadać na pytania co się stalo i co się dzieje teraz przy uzyciu reproducibilnych zapytań PromQL, LogQL i trace search.
semantic-drift-auditor
Modernization auditor designed to prevent business terminology decay and semantic drift. Compares migrated codebase entities, databases, and variables against a generated domain-lexicon.json mapped from specs/REQS.md. Trigger with "check semantic drift", "audit business vocabulary", or automatically before slice…