What is tsz-project-bench?

A benchmark and project-compatibility guide for TSZ. A benchmark measures performance or compatibility, while a project corpus tests the compiler against real software projects.

It is for investigating benchmark rows, compiler checks, fixture metadata, performance setup, and compatibility with projects such as RxJS, Zod, Next, and Vite.

It helps separate correctness failures from speed, timeout, memory, metadata, and website-data problems before optimization begins.

How tsz-org/tsz configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to tsz-org/tsz. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/tsz-org/tsz/main/.agents/skills/tsz-project-bench/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tsz-org/tsz

Made for: Claude Code, Codex.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-project-bench/github.svg)](https://agentmods.dev/skills/tsz-org/tsz/tsz-project-bench)

Your own site

<a href="https://agentmods.dev/skills/tsz-org/tsz/tsz-project-bench"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-project-bench/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/tsz-org/tsz/tsz-project-bench"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-project-bench.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 79 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 548 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00079	$0.00548
Opus 5.5	$0.00032	$0.00219
Sonnet 5.5	$0.00016	$0.00110
Haiku 4.5	$0.00008	$0.00055

Measured 23d ago against content hash ee82500a5598, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tsz-project-bench 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 23d 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.

.agents/skills/tsz-project-bench/SKILL.md · 52 lines

What it actually says

TSZ Project Bench

Use for project-corpus rows, benchmark harness, fixture metadata, PGO bench setup, and website benchmark data.

Rules

Read AGENTS.md and docs/plan/ROADMAP.md for durable benchmark/project work.
Inspect overlapping PRs/issues.
Red row = correctness blocker before speed problem unless failure is runtime, residency, timeout, or OOM.
Keep fixture metadata shared across project-fixtures.sh, bench-vs-tsgo.sh, and project-compile-guard.sh.
Wrap long/heavy local commands with scripts/safe-run.sh.

Sources

scripts/bench/project-fixtures.sh
scripts/bench/bench-vs-tsgo.sh
scripts/ci/project-compile-guard.sh
crates/tsz-website/src/_data/benchmark_data.js
.github/workflows/bench.yml

Workflow

Identify row, phase, and first failure: prepare, tsc validation, tsz check, emit scope, crash, timeout, OOM, metadata, website ingestion, timing.
Required/canary/all set: TSZ_PROJECT_COMPILE_SET=<required|canary|all>.
Reproduce with the narrowest filter.
If typecheck fails, reduce to owning compiler operation before optimizing.
For speed work, name repeated operation and complexity change. No fixture-name special cases.

Commands

./scripts/bench/bench-vs-tsgo.sh --prepare-only
./scripts/bench/bench-vs-tsgo.sh --quick --filter "<row>" --json-file /tmp/bench.json
TSZ_PROJECT_COMPILE_FILTER="<row>" TSZ_PROJECT_COMPILE_SET=required scripts/ci/project-compile-guard.sh
TSZ_PROJECT_COMPILE_ALLOW_FAILURES=1 TSZ_PROJECT_COMPILE_SET=all scripts/ci/project-compile-guard.sh

PR notes: goal (green, fast, or grow), row, before/after failure class, first broken phase, owner layer, fixture metadata changes, whether timing is meaningful, commands/CI links.

Changes

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.

23d ago First seen · 52 lines · 79 tokens per session scan A ee82500a5598

Subscribe to this mod's changes

tsz-project-bench is a skill published in the GitHub repository tsz-org/tsz (577 stars, last pushed today), licensed Apache-2.0. It adds 79 tokens to every session and 548 once invoked, about $0.0003 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 2026-09-28.

Analytics and metrics Languages Rust TypeScript

ax-rust-signature

Use when writing Rust code with axllm for string signatures, field descriptors, JSON schema output, validation, and typed tool argument shapes.

ax-llm/ax · 36 tokens

dd-code-generation

Use pup CLI for immediate Datadog operations or generate code for integration into applications.

DataDog/pup · 16 tokens

ax-rust-llm

Use when writing Rust code with axllm for using the generated Ax package, factory functions, package docs, examples, and API reference.

ax-llm/ax · 37 tokens

solana-toolkit-guide

Guide to the Solana Wallet Toolkit — vanity address generation with multi-threaded search, official Solana Labs libraries, Rust and TypeScript implementations. Includes wallet generation, custom address prefixes, and OG names on the blockchain.

nirholas/three.ws · 50 tokens

solana

Use when working on Solana software, including one or more of: Solana client code using TypeScript, Rust libraries that use Solana crates, Anchor programs, Quasar programs, LiteSVM tests, including Rust program files, TypeScript tests, and Anchor.toml or Quasar.toml configuration. Designed to create minimal, reusable…

quicknode/solana-finance-claude-plugin · 76 tokens

docstring-generator

Generate and update language-idiomatic doc comments for TypeScript (TSDoc/JSDoc) and Rust (Rustdoc). Use when asked to "add docs", "document this file", "generate docstrings", "add JSDoc", "add Rustdoc", "write TSDoc", or when working with TypeScript or Rust source files that need documentation comments. Supports…

espennilsen/pi · 118 tokens

tsz: Skill for Claude Code