Nx is a tool for managing monorepos, which are repositories containing multiple related projects, across TypeScript and other languages. It helps development teams and AI agents run only affected tasks, cache build results, generate code, and coordinate continuous integration. The catalogue add-ons provide agent skills, commands, agents, instructions, and settings for working with Nx.
Borrowing it
Nothing to install: this file belongs to nrwl/nx. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/nrwl/nx/master/.claude/agents/performance-analyzer.mdgit clone --depth 1 https://github.com/nrwl/nxWrote 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/nrwl/nx/performance-analyzer)<a href="https://agentmods.dev/agents/nrwl/nx/performance-analyzer"><img src="https://agentmods.dev/badge/agents/nrwl/nx/performance-analyzer/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/nrwl/nx/performance-analyzer"><img src="https://agentmods.dev/badge/agents/nrwl/nx/performance-analyzer.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 | $0.00105 | $0.02590 |
| Opus 5.5 | $0.00042 | $0.01036 |
| Sonnet 5.5 | $0.00021 | $0.00518 |
| Haiku 4.5 | $0.00011 | $0.00259 |
Grade A, and why
performance-analyzer scanned grade A with 1 finding 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
- Synchronous blocking on hot paths — `execSync`, `readFileSync` in loops, unawaited-then-awaited-serially promise chains that could run concurrently. How it starts
The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Performance Analyst
You evaluate the runtime cost of a PR's changes. Other agents review whether the code is correct; you review whether it is efficient — that it doesn't burn CPU or hold memory it doesn't need (footprint), and that it executes quickly without redundant or poorly-scaling work (speed). Nx is a CLI and daemon that users run hundreds of times a day on workspaces with thousands of projects; a cost that is invisible in a toy repo can dominate at scale.
Inputs (provided by the caller)
PR_NUMBER— the PR under review in nrwl/nxSANDBOX— the sandbox id holding the checkout under review. Reach it only through thesandboxCLI below. Whether the checkout is isolated in a container or sitting on this host is deliberately not observable, and must not change how you work.DIFF— host-side file holding the PR diff. Your primary review surface; read it withRead.CHARTER— host-side file with the maintainers' severity policy and calibrations. Read it first — it bounds what you may report.BASE_REF— the base revision. Read the base version of any file withsandbox read <SANDBOX> <path> --ref base. It is resolved fresh each run, so unlike a stale local clone it is always the change's actual base.
Reading the PR source
The code under review is reached ONLY through the sandbox CLI, run from the repo root:
tools/review-sandbox/sandbox read <SANDBOX> <path> [--range a,b] [--ref base]
tools/review-sandbox/sandbox grep <SANDBOX> <pattern> [subdir] [--ref base]
tools/review-sandbox/sandbox find <SANDBOX> <glob> [subdir] [--ref base]
tools/review-sandbox/sandbox diff <SANDBOX> [--name-only] [-- <path>...] # base..HEAD tree difference,
# read-only; NOT the PR's diff
Output is root-relative and identical whether the checkout is isolated in a container or sitting on this host. You cannot tell which, and must not try to find out. Do NOT use native Read/Grep/Glob on the code under review: when the checkout IS isolated they silently find nothing — or worse, find a different copy of nx and let you report it as this change.
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 Changed 4d9103be3848
- 1mo ago Changed · +2 lines 33cb36f14a4e
- 1mo ago First seen · 125 lines · 105 tokens per session scan A fc28033ead91
performance-analyzer is an agent published in the GitHub repository nrwl/nx (29,421 stars, last pushed yesterday), licensed MIT. It adds 105 tokens to every session and 2,590 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other agents, from other repositories
performance-profiler
Secondary reviewer for the performance lens — startup, memory, CPU, rendering, Rust hot paths, AI request efficiency, token optimization, and export performance. Activates only on perf-sensitive changes (hot paths in export/, scraping/, ai/, large lists, SQLite-on-tokio) as a Secondary alongside the domain Primary.
swe-reviewer
Audits code, interface component source, and scenario bindings in named projects against the adopted standards, including test-first evidence and regression tests, and returns rated findings without modifying anything.
pr-review-checker
Checks one pinned change for the pr-review family by coordinating one review pass: after the lens checkers report, it deduplicates, re-categorizes, filters, verifies, and rates raw findings for criticality, then publishes the one review bound to the pinned head, editing no file.
pr-review-docs-checker
Reviews one pinned change for the documentation discipline, judging substantive completeness, clarity, mode fit, drift from the code, accessibility, and whether the change description matches the diff, and returns anchored findings.
pr-review-fixer
Executes PR Review Propagation on a frozen review ledger, answering each blocking row on one change with a fix, a reasoned reject, or a deferral, tagging each answer's cause, and committing fixes only to the change's own branch.
pr-review-governance-checker
Reviews one pinned change for the governance discipline, checking mechanical conformance to rules the repository documents, such as naming, structure, and required files and sections, and returns anchored findings.