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 pledgeandgrow/pledge-skills --skill oxcgit clone --depth 1 https://github.com/pledgeandgrow/pledge-skillsWrote 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/pledgeandgrow/pledge-skills/oxc)<a href="https://agentmods.dev/skills/pledgeandgrow/pledge-skills/oxc"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/oxc/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/pledgeandgrow/pledge-skills/oxc"><img src="https://agentmods.dev/badge/skills/pledgeandgrow/pledge-skills/oxc.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 | $0.00131 | $0.01704 |
| Opus 5 | $0.00066 | $0.00852 |
| Sonnet 5 | $0.00026 | $0.00341 |
| Haiku 4.5 | $0.00013 | $0.00170 |
Grade A, and why
oxc-docs 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 10d 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 — 157 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oxc Expert
Official Documentation: https://oxc.rs/docs/guide/introduction.html Learn (Parser Tutorial): https://oxc.rs/docs/learn/parser_in_rust/intro.html GitHub: https://github.com/oxc-project/oxc Playground: https://playground.oxc.rs
What is Oxc?
Oxc (The JavaScript Oxidation Compiler) is a collection of high-performance JavaScript tools written in Rust. It includes:
- Parser — Fastest JS/TS parser, 3x faster than swc parser
- Linter (Oxlint) — 840+ rules, 50-100x faster than ESLint, ESLint-compatible
- Formatter (Oxfmt) — Prettier-compatible formatter
- Transformer — TS type stripping, JSX, decorators, lowering (ES2026→ES2015)
- Minifier — Dead code elimination, mangling, syntax normalization
- Resolver — 28x faster than webpack/enhanced-resolve
Quick Reference
| Topic | File |
|---|---|
| Lexer, AST, Parser, Errors, Semantic Analysis tutorial | oxc-parser-tutorial.md |
| Parser, Linter, Test Infrastructure, AST Tools architecture | oxc-architecture.md |
| ECMAScript Specification, Grammar quirks | oxc-ecmascript.md |
| Performance optimization techniques | oxc-performance.md |
| Tool usage guide (parser, linter, formatter, transformer, minifier, resolver) | oxc-usage-guide.md |
Compiler Frontend Pipeline
Source Text --> Lexer --> Token --> Parser --> AST
Philosophy
- Performance is a feature — speed is a product requirement; regressions are bugs
- One toolchain, shared building blocks — all tools built on shared components for consistency
- Correctness with clear boundaries — differences from other tools are documented
- Practical developer experience — sensible defaults, understandable config, stable output
Core Design Principles
- Allocate less memory — use memory arenas (bumpalo), string inlining (CompactString)
- Use fewer CPU cycles — SIMD for whitespace, small enum sizes, cache-friendly layouts
- Zero-cost abstractions — Rust's abstractions compile to efficient machine code
- Composition over inheritance — no inheritance in Rust; use traits and composition
- Two-phase design — parse to AST first, then semantic analysis separately
What ships with it
5 files 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.
- 10d ago First seen · 157 lines · 131 tokens per session scan A 9de0d3fb7fa9
oxc-docs is a skill published in the GitHub repository pledgeandgrow/pledge-skills (10 stars, last pushed 1mo ago), licensed MIT. It adds 131 tokens to every session and 1,704 once invoked, about $0.0007 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
insta-snapshots
Guide for working with and updating insta snapshot tests in Oxc without terminal interaction.
migrate-oxfmt
Guide for migrating a project from Prettier or Biome to Oxfmt. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's formatter from Prettier or Biome to Oxfmt.
migrate-oxlint
Guide for migrating a project from ESLint to Oxlint. Use when asked to migrate, convert, or switch a JavaScript/TypeScript project's linter from ESLint to Oxlint.
performance-lint-rules
Performance review guidance for Oxc linter rule implementations. Use only when reviewing Rust rule code under crates/oxclinter/src/rules/ or when explicitly auditing those rules for performance improvements.
handle-regression
Protocol for detecting, isolating, and fixing regressions in test262 pass count. Use when a test run shows fewer passes than expected.
regression-triage
Bulk-classify a list of test262 pass→other transitions from a CI run. Distinct from handle-regression (single fix) and analyze-regression (diff two runs). Use after a merge wave when the sharded run reports N regressions and you need to bucket them by root cause and decide which are false positives.