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/delexw/claude-code-misc/oxlintnpx skills add delexw/claude-code-misc --skill oxlintgit clone --depth 1 https://github.com/delexw/claude-code-miscWhat 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 | $0.00111 | $0.02079 |
| Opus 5 | $0.00056 | $0.01040 |
| Sonnet 5 | $0.00022 | $0.00416 |
| Haiku 4.5 | $0.00011 | $0.00208 |
Grade A, and why
oxlint 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 2d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Oxlint — High-Performance JS/TS Linter
Oxlint is 50-100x faster than ESLint. It ships with 690+ rules covering ESLint core, TypeScript, React, Jest, Unicorn, jsx-a11y, and more. It prioritizes high-signal correctness checks by default — things that are incorrect, unsafe, or useless — so teams can adopt it without drowning in false positives.
Detection
Before linting, confirm the project uses oxlint by checking for any of:
oxlintinpackage.jsondevDependencies/dependencies- An
.oxlintrc.jsonfile in the project root - An
oxlint.config.tsfile in the project root - An
oxlintorlintscript inpackage.jsonthat referencesoxlint
If none of these exist, the project doesn't use oxlint — don't run it.
Running Oxlint
After code changes
Run oxlint to check your work. Prefer the project's npm script if one exists:
# If package.json has a lint script using oxlint
npm run lint
# Otherwise, run directly
npx oxlint
Fixing issues automatically
npx oxlint --fix
Use --fix for safe automatic fixes. Avoid --fix-dangerously unless the user explicitly asks for it — it can apply unsafe transformations.
Linting specific files
After editing only a few files, you can lint just those:
npx oxlint src/components/Button.tsx src/utils/helpers.ts
Interpreting output
Oxlint prints diagnostics with rule names in parentheses, e.g. (no-unused-vars). When fixing:
- Read the diagnostic message carefully — oxlint gives precise, actionable information
- Fix the underlying code issue rather than suppressing the rule
- Only add
// oxlint-ignorecomments as a last resort when the diagnostic is a genuine false positive
Output formats
For CI or tooling integration:
npx oxlint --format json # Machine-readable JSON
npx oxlint --format github # GitHub Actions annotations
npx oxlint --format unix # Simple one-line-per-error format
Configuration
Creating a config
npx oxlint --init
This generates an .oxlintrc.json starter config.
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.
- 2d ago First seen · 231 lines · 111 tokens per session scan A 2bb36d27249b
oxlint is a skill published in the GitHub repository delexw/claude-code-misc (1 stars, last pushed 5mo ago), licensed MIT. It adds 111 tokens to every session and 2,079 once invoked, about $0.0006 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
chat-sdk
Build multi-platform chat bots with Chat SDK (chat npm package). Use when developers want to (1) Build a Slack, Teams, Google Chat, Discord, Telegram, GitHub, Linear, or WhatsApp bot, (2) Use Chat SDK to handle mentions, direct messages, subscribed threads, reactions, slash commands, cards, modals, files, or AI…
stack-trace-js-probe
Internal helper for meta-stack-trace-investigator. Use when a JavaScript or TypeScript stack trace needs npm/node/tsc-specific checks, reproduction guidance, and patch targets.
new
Create a new project to start development quickly.
adk
Use this skill when you've got questions about the Botpress Agent Development Kit (ADK) - like when you're building a feature that involves tables, actions, tools, workflows, conversations, files, knowledge bases, triggers, or Zai.
xcode-compilation-analyzer
Analyze Swift and mixed-language compile hotspots using build timing summaries and Swift frontend diagnostics, then produce a recommend-first source-level optimization plan. Use when a developer reports slow compilation, type-checking warnings, expensive clean-build compile phases, long CompileSwiftSources tasks…
antfu
Anthony Fu's opinionated tooling and conventions for JavaScript/TypeScript projects. Use when setting up new projects, configuring ESLint/Prettier alternatives, monorepos, library publishing, or when the user mentions Anthony Fu's preferences.