preflight-checks

preflight-checks is a skill for Claude Code, Codex from rileyhilliard/agentrc. It costs 35 tokens per session (830 once invoked), scanned A, original, MIT.

A pre-commit check that finds and runs a project's linters, formatters, and type checkers.

In plain words
What is it for?
It is for checking JavaScript, TypeScript, Python, and other projects using tools configured in their files.
Why use it?
It catches style, formatting, and type errors before they reach a commit or are reported as completed work.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit It is for checking JavaScript, TypeScript, Python, and other projects using tools…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/rileyhilliard/agentrc/preflight-checks
Install

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.

Any agent
npx skills add rileyhilliard/agentrc --skill preflight-checks
Clone the repo
git clone --depth 1 https://github.com/rileyhilliard/agentrc

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.

agentmods badge for preflight-checks

README.md
[![agentmods](https://agentmods.dev/badge/skills/rileyhilliard/agentrc/preflight-checks.svg)](https://agentmods.dev/skills/rileyhilliard/agentrc/preflight-checks)
Your own site
<a href="https://agentmods.dev/skills/rileyhilliard/agentrc/preflight-checks"><img src="https://agentmods.dev/badge/skills/rileyhilliard/agentrc/preflight-checks.svg" alt="Measured on agentmods" height="20"></a>
Per session 35 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 830 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00035 $0.00830
Opus 5 $0.00017 $0.00415
Sonnet 5 $0.00007 $0.00166
Haiku 4.5 $0.00003 $0.00083

Measured 6d ago against content hash 4eacf3792299, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

preflight-checks 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 6d 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.

.agentrc/skills/preflight-checks/SKILL.md · 77 lines

How it starts

The opening of the file, as written. The whole thing — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Preflight Checks

Run the project's code quality tools before committing. Catch errors early instead of letting pre-commit hooks catch them.

Tool Detection

Detect available tools from project config files. Check in this order:

Config File Tool Check Command Fix Command
package.json scripts npm/yarn/pnpm Look for lint, typecheck, format, check scripts Run with --fix where available
.eslintrc* / eslint.config.* ESLint npx eslint <files> npx eslint --fix <files>
tsconfig.json TypeScript npx tsc --noEmit Manual fix required
.prettierrc* / prettier in package.json Prettier npx prettier --check <files> npx prettier --write <files>
pyproject.toml with [tool.ruff] Ruff ruff check <files> ruff check --fix <files> && ruff format <files>
pyproject.toml with [tool.mypy] / mypy.ini mypy mypy <files> Manual fix required
pyproject.toml with [tool.black] Black black --check <files> black <files>
.flake8 / setup.cfg with [flake8] Flake8 flake8 <files> Manual fix required
go.mod Go go vet ./... gofmt -w <files>
Cargo.toml Rust cargo clippy cargo clippy --fix
.pre-commit-config.yaml pre-commit pre-commit run --files <files> Runs auto-fix internally

Execution Order

Run tools in this order. Each step can change code that later steps check.

  1. Formatters (auto-fix): prettier, black, ruff format, gofmt
  2. Linters (auto-fix where possible): eslint --fix, ruff check --fix
  3. Type checkers (manual fix): tsc, mypy, pyright

Scope

Only check files that are staged or modified. Don't run checks on the entire codebase.

# Staged files
git diff --cached --name-only --diff-filter=ACM

# Unstaged modified files
git diff --name-only --diff-filter=ACM

Filter to relevant extensions for each tool (e.g., only .ts/.tsx for tsc, only .py for ruff).

Read the full file on GitHub · 77 lines

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. 6d ago First seen · 77 lines · 35 tokens per session scan A 4eacf3792299

Subscribe to this mod's changes

preflight-checks is a skill published in the GitHub repository rileyhilliard/agentrc (3 stars, last pushed 6mo ago), licensed MIT. It adds 35 tokens to every session and 830 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.