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 Arnosdeus/agent-toolkit --skill performance-reviewgit clone --depth 1 https://github.com/Arnosdeus/agent-toolkitWrote 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/arnosdeus/agent-toolkit/performance-review)<a href="https://agentmods.dev/skills/arnosdeus/agent-toolkit/performance-review"><img src="https://agentmods.dev/badge/skills/arnosdeus/agent-toolkit/performance-review/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/arnosdeus/agent-toolkit/performance-review"><img src="https://agentmods.dev/badge/skills/arnosdeus/agent-toolkit/performance-review.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 | $0.00030 | $0.00178 |
| Opus 5.5 | $0.00012 | $0.00071 |
| Sonnet 5.5 | $0.00006 | $0.00036 |
| Haiku 4.5 | $0.00003 | $0.00018 |
Grade A, and why
performance-review 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.
What it actually says
Performance Review
Procedure and output
Establish a baseline or reproducible cost before recommending a change. Report
BLOCKER, MAJOR, MINOR, or NOTE findings with metric, trace, query, or
code evidence, plus the smallest justified remediation.
Look for measurable bundle and dependency cost, unnecessary re-renders, requests, missing caching, image inefficiency, inappropriate lazy loading or code splitting, slow queries/N+1 patterns, API latency, memory growth, polling, and loading behavior. Prefer traces, metrics, profiling, query plans, or reproducible measurements. Do not recommend speculative optimization; state the measurement needed when evidence is unavailable.
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 · 20 lines · 30 tokens per session scan A 9ed05ab68c84
performance-review is a skill published in the GitHub repository Arnosdeus/agent-toolkit (2 stars, last pushed 1mo ago), licensed MIT. It adds 30 tokens to every session and 178 once invoked, about $0.0001 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 skills, from other repositories
fix
Fix a bug grounded in Hunch (past root causes, constraints, blast radius).
bug-report-reproduce
Reproduce a user, customer, or support-reported problem with synthetic data, prove the cause with a temporary test, record a narrated click-through walkthrough of the symptom, and report what was and was not proven. Use when the user links a bug report, support thread, or ticket and asks to reproduce it, find the…
changes-explain
Explain a pull request, commit range, branch, or local diff from a system-design perspective. Use for practical understanding of changed behavior, boundaries, flow, ownership, operations, risks, and verification rather than defect review.
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior — before proposing fixes.
k-issue
A workflow for reproducing and diagnosing an existing software failure. After receiving permission to fix it, it proves the same symptom before and after the fix.
agenttrace-session-audit
Audit local AI coding-agent sessions with agenttrace for cost, tool failures, latency, anomalies, health, diffs, and CI gates.