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 agentmods add skills/nicolasyusim/better-codebase/better-performancenpx skills add NicolasYusim/better-codebase --skill better-performancegit clone --depth 1 https://github.com/NicolasYusim/better-codebaseWhat 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 | $0.00079 | $0.01210 |
| Opus 5 | $0.00039 | $0.00605 |
| Sonnet 5 | $0.00016 | $0.00242 |
| Haiku 4.5 | $0.00008 | $0.00121 |
Grade A, and why
better-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 2d 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 — 139 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve performance only where evidence points
Optimize against an explicit workload, constraint, or established complexity problem. Protect correctness and clarity while reducing a measured cost.
Own proven performance problems
Own latency, throughput, CPU, memory, allocation, I/O, query, network, serialization, bundle, and scaling findings supported by measurement or a clearly established complexity issue.
Do not own general code cleanliness, dependency freshness, or architectural preference. Route those root causes to their owning skills and mention performance only as a secondary effect when it is not measured.
Evidence gate
Accept a performance finding only with at least one:
- profiler, trace, query plan, bundle report, or production metric tied to the scope;
- reproducible benchmark using a representative workload;
- observed call or query count that establishes repeated work;
- demonstrated resource growth or leak;
- a complexity argument with realistic unbounded or sufficiently large input;
- a documented latency, memory, throughput, or size budget that the current result exceeds.
Source-code suspicion without one of these becomes a measurement candidate, not a finding.
Review workflow
1. Define the performance contract
Identify the workload, input size, concurrency, environment, warm or cold state, cache state, percentile or aggregate, and required budget. State what users or systems experience when the budget is missed.
If no contract exists, define a measurement question instead of inventing a target.
2. Establish the baseline
Use existing benchmarks, observability, profilers, database tooling, browser tooling, or package analyzers where available. Keep measurement safe and proportionate.
Record:
- exact command or interaction;
- environment and representative fixture;
- repetitions, warmup, and variance when meaningful;
- baseline time, memory, count, throughput, or size;
- important exclusions and noise sources.
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.
- 2d ago First seen · 139 lines · 79 tokens per session scan A 719f5ab8f848
better-performance is a skill published in the GitHub repository NicolasYusim/better-codebase (1 stars, last pushed 23d ago), licensed MIT. It adds 79 tokens to every session and 1,210 once invoked, about $0.0004 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
issue-triage
Issue triage: audit open issues, categorize, detect duplicates, cross-ref PRs, risk assessment, post comments. Args: "all" for deep analysis of all, issue numbers to focus (e.g. "42 57"), "en"/"fr" for language, no arg = audit only in French.
performance
CLI performance optimization - startup time, memory usage, token savings benchmarking.
build-teaql-app
Build or change a TeaQL application in Java, Rust, Go, Swift, Python, C#/.NET, or TypeScript, including Kotlin/JVM applications that consume Java-generated libraries. Mandatory order: first draft and save a complete KSML model, then verify the client and evaluate that saved model, repair it through repeated evaluation…
orchestrator-lanes
Claude Code dev-orchestrator only. File-based multi-lane PM playbook (score, DAG, run-controller, L0/L1/L2, ship). Use when this session IS that agent, or user says info / справка / lane-stack:orchestrator-lanes info. SKIP: Grok, Codex, Kimi, Qwen, AGY, Cursor writer CLIs and any default coding agent — do not load, do…
self-assessment
Interactive skill assessment with personalized learning path generation.
source-command-methodology-advisor
Analyzes your codebase and asks 3 targeted questions to recommend the right AI-assisted development methodology stack.