agentmods.dev

opal: Skill for Claude Code

.claude/skills/lint-and-format/SKILL.md

lint-and-format is a skill for Claude Code from matteing/opal. It costs 36 tokens per session (443 once invoked), scanned A, original, MIT.

A pre-commit checking routine that runs a project's code-quality checks for formatting and linting. Linting finds common code problems, while formatting makes code follow consistent style rules.

In plain words
What is it for?
Use it after changing Elixir, TypeScript, or JavaScript code to check or fix formatting and lint errors before committing.
Why use it?
It catches style and quality problems before code is committed or rejected by automated checks. It can also apply the supported fixes and asks you to review the result.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

This is matteing/opal's own configuration. It tells Claude Code how to work on opal itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything opal configures →

not rated 62repo 2mo ago A scan SkillSpector: pass 36 tokens original MIT
View source ↗ matteing/opal
Reuse

Borrowing it

Nothing to install: this file belongs to matteing/opal. 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/matteing/opal/main/.claude/skills/lint-and-format/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/matteing/opal

Made for: Claude Code.

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.

agentmods badge for lint-and-format

README.md
[![agentmods](https://agentmods.dev/badge/skills/matteing/opal/lint-and-format/github.svg)](https://agentmods.dev/skills/matteing/opal/lint-and-format)
Your own site
<a href="https://agentmods.dev/skills/matteing/opal/lint-and-format"><img src="https://agentmods.dev/badge/skills/matteing/opal/lint-and-format/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.

agentmods 80×15 button for lint-and-format

Your own site · 80×15
<a href="https://agentmods.dev/skills/matteing/opal/lint-and-format"><img src="https://agentmods.dev/badge/skills/matteing/opal/lint-and-format.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 443 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00036 $0.00443
Opus 5.5 $0.00014 $0.00177
Sonnet 5.5 $0.00007 $0.00089
Haiku 4.5 $0.00004 $0.00044

Measured 2mo ago against content hash 6e44cac64906, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

lint-and-format 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 2mo 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.

.claude/skills/lint-and-format/SKILL.md · 68 lines

What it actually says

Lint & Format Skill

You ensure all code passes the project's linters and formatters before it gets committed. This mirrors the lefthook pre-commit hooks and CI checks so problems are caught immediately.

When to act

  • After writing or modifying any source file, before creating a commit.
  • When the user asks to fix lint or formatting issues.
  • When a commit or CI fails due to formatting.

Commands

Elixir (lib/, test/, config/)

# Check formatting (what CI runs)
mise run lint:core

# Auto-fix formatting
mise run format:core

TypeScript/JavaScript (cli/)

# ESLint check
cd cli && pnpm lint

# ESLint auto-fix
cd cli && pnpm lint:fix

# Prettier check
cd cli && pnpm format:check

# Prettier auto-fix
cd cli && pnpm format

Run everything

# Check all (what CI runs)
mise run lint

# Fix all
mise run format

Workflow

  1. After making code changes, run the relevant lint/format check commands.
  2. If there are failures, auto-fix them using the fix variants.
  3. If auto-fix changes files, review the diff to make sure nothing unexpected changed.
  4. Only then proceed with staging and committing.

Rules

  1. Never commit code that fails linting or formatting checks.
  2. Prefer auto-fix (mise run format, lint:fix) over manual edits when possible.
  3. If a lint rule seems wrong for a specific case, discuss with the user before adding a suppression comment.
  4. Do not disable or weaken lint rules without explicit approval.
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.

  1. 2mo ago First seen · 68 lines · 36 tokens per session scan A 6e44cac64906

Subscribe to this mod's changes

lint-and-format is a skill published in the GitHub repository matteing/opal (62 stars, last pushed 2mo ago), licensed MIT. It adds 36 tokens to every session and 443 once invoked, about $0.0001 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 2026-08-30.

Code reviewGit and workflowLLMagentsaiai-agentsclielixir
Related

lint-and-format compared with skills from other repositories

lint-and-format next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
lint-and-formatmatteing/opalSkill622mo agoMITA36Claude Code
hunk-launch-videomodem-dev/hunkSkill9.8kyesterdayMITA60Claude Code, Codex
otto-pr-review-loopomnigent-ai/omnigentSkill11kyesterdayApache-2.0A17Claude Code, Codex
hunk-releasemodem-dev/hunkSkill9.8kyesterdayMITA38Claude Code, Codex
resolve-drive-promnigent-ai/omnigentSkill11kyesterdayApache-2.0A21Claude Code, Codex
describe-prhumanlayer/humanlayerSkill13kyesterdayApache-2.0A15Claude Code, Codex
feature-publishomnigent-ai/omnigentSkill11kyesterdayApache-2.0A24Claude Code, Codex