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 louisbrulenaudet/monorepo-template --skill review-performancegit clone --depth 1 https://github.com/louisbrulenaudet/monorepo-templateWrote 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/louisbrulenaudet/monorepo-template/review-performance)<a href="https://agentmods.dev/skills/louisbrulenaudet/monorepo-template/review-performance"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-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/louisbrulenaudet/monorepo-template/review-performance"><img src="https://agentmods.dev/badge/skills/louisbrulenaudet/monorepo-template/review-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 | $0.00040 | $0.01978 |
| Opus 5 | $0.00020 | $0.00989 |
| Sonnet 5 | $0.00008 | $0.00396 |
| Haiku 4.5 | $0.00004 | $0.00198 |
Grade A, and why
review-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 12d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review performance
Run a performance-focused review: algorithmic complexity, data structures, memory leaks, bundle size, critical path, cache strategy, images, and Worker cold starts. Your reply must be a plan of suggested changes: concise, actionable, and structured-not only prose.
Invocation
Text after the slash command is additional scope/focus - narrow the review accordingly. If none given, use the default scope described below.
Best practices alignment
- Algorithms and data structures - Prefer O(n) or better for hot paths; avoid redundant loops, repeated sorts, or nested iterations over large collections; use appropriate structures (Map/Set for lookups, avoid repeated array scans).
- Memory - No closure or WeakRef leaks in long-lived Workers; no unbounded caches or growing global state; React effects and subscriptions cleaned up on unmount.
- Frontend - Critical path minimal; lazy load below-the-fold;
fetchpriorityfor LCP; explicit dimensions to avoid CLS; code-splitting and tree-shaking; prefetch where beneficial. - Caching - Cache TTLs and keys match content type (HTML vs assets vs API); no over-caching of dynamic content or under-caching of static; Cloudflare asset and API cache headers correct.
- Worker and API - Bundle size within limits (e.g. < 1 MB compressed for Workers); no blocking I/O on critical path; cold start impact minimized (small deps, no heavy init).
Align with root AGENTS.md and app AGENTS.md for build and deployment model.
Deep technical review
Conduct a performance-only review. Inspect the following and call out violations or improvements.
Algorithmic complexity and data structures
- Artifacts: apps/front-app/src/utils/ and other hot paths, apps/worker-api/src/ (routes, handlers).
- Checks: No O(n²) or worse in hot paths. Filter/map/reduce chains: single pass where possible; avoid repeated
.find()in loops (use Map). Sort once and reuse; avoid heavy work in render. Pagination or limits on large lists. worker-api: no N+1 patterns; batch or single queries where appropriate.
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.
- 12d ago First seen · 128 lines · 40 tokens per session scan A 8afb3ec48de9
review-performance is a skill published in the GitHub repository louisbrulenaudet/monorepo-template (19 stars, last pushed 11d ago), licensed Apache-2.0. It adds 40 tokens to every session and 1,978 once invoked, about $0.0002 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
cause-and-effect
Systematic Fishbone analysis exploring problem causes across six categories.
root-cause-tracing
Use when errors occur deep in execution and you need to trace back to find the original trigger - systematically traces bugs backward through call stack, adding instrumentation when needed, to identify source of invalid data or incorrect behavior.
why
Iterative Five Whys root cause analysis drilling from symptoms to fundamentals.
refactor
Make the same change across many files safely. Use when renaming a symbol, changing a call signature, moving a pattern, or applying a consistent edit to a whole codebase.
code-search
Find where something lives in an unfamiliar Workspace. Use when asked where a function, symbol, config value, or piece of behaviour is defined, or when you need to understand a codebase's layout before changing it.
debug
Structured debugging assistant. Use /debug to get a guided diagnosis of any bug — Claude will ask the right questions and then pinpoint the root cause.