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/goldziher/poly/poly-overviewnpx skills add Goldziher/poly --skill poly-overviewgit clone --depth 1 https://github.com/Goldziher/polyWrote 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/goldziher/poly/poly-overview)<a href="https://agentmods.dev/skills/goldziher/poly/poly-overview"><img src="https://agentmods.dev/badge/skills/goldziher/poly/poly-overview.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.00983 |
| Opus 5 | $0.00016 | $0.00491 |
| Sonnet 5 | $0.00007 | $0.00197 |
| Haiku 4.5 | $0.00003 | $0.00098 |
Grade A, and why
poly-overview 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 4d 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 — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
poly Overview
poly is a single pure-Rust binary that lints and formats a whole repository across languages. It wraps best-in-class tools as in-process crate backends and falls back to a tree-sitter generic tier for everything else, so it runs the same on any machine and in CI. No system tool is ever required; the one scoped exception is the native-toolchain tier below, which uses a language's canonical CLI when it happens to be installed.
Per-language coverage tiers
- Tier 1 — native in-process backends. Highest fidelity, compiled straight into the
binary and registered per language in
registry.rs:ruff(Python),oxc(JS/TS/JSX/TSX/JSON/JSONC),taplo(TOML),rumdl(Markdown/MDX),sqruff(SQL), YAML,malva(CSS/SCSS/LESS) +biome(CSS/SCSS),markup_fmt(HTML/Vue/Svelte/Astro/Angular/Jinja/ Vento/Mustache/XML),mago(PHP),rubyfmt(Ruby),graphql+biome(GraphQL),nixfmt(Nix),hcl, Dockerfile, dotenv, and INI. - Tier 2 — tree-sitter generic tier. The catch-all for the long tail (Elixir, C/C++,
C#, protobuf, and the rest of 300+ grammars). CST-driven structural reindent for
brace-family grammars, whitespace normalization otherwise, and a
LEAVE_UNTOUCHEDlist for grammars where whitespace is significant. Best-effort, pure Rust, grammars loaded on demand — never gofmt/rustfmt parity, by design. - Native-toolchain tier (scoped exception). A language's canonical first-party CLI run
per file over stdin/stdout when installed:
rustfmt,gofmtandshellcheckare on by default when found on PATH;zig fmt,shfmt,google-java-format,ktfmt,styler(R),swift-format,dart format, andgleam formatare opt-in via[fmt.<lang>.<tool>] enabled = true/[lint.<lang>.<tool>] enabled = true. When the tool is absent, formatting falls through to tier 2 with an info-level notice, so the zero-dependency guarantee always holds.
Cross-cutting engines (every language)
Four engines are appended to every language regardless of tier:
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.
- 4d ago First seen · 59 lines · 33 tokens per session scan A e70df895367f
poly-overview is a skill published in the GitHub repository Goldziher/poly (10 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 983 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 2026-08-31.
Other skills, from other repositories
Biome
Biome 2.x — fast all-in-one web toolchain in Rust. Formats, lints, assists. Replaces Prettier + ESLint.
prettier-docs
Prettier 3.9.5 — opinionated code formatter. CLI, API, config, plugins, editor integration, CI.
ruff-docs
Ruff — fast Python linter and formatter in Rust. 900+ rules, Black-compatible formatter, LSP, CI/CD.
ESLint for Test Quality
Enforce test quality with ESLint - eslint-plugin-jest, eslint-plugin-playwright, and eslint-plugin-testing-library rules in flat config, blocking focused tests, missing assertions, and flaky waits via a CI lint gate.
lint-and-fix
自动Lint修复技能 - 运行Linter、解析错误、AI自动修复循环.
ci-formats-review
Review SARIF, CodeClimate, compact, markdown, badge, and other CI-facing output formats for correctness and integrator expectations. Use when changes affect machine-consumed report formats or CI presentation layers.