Borrowing it
Nothing to install: this file belongs to mirekondro/The-Pre-Flight-Check. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/mirekondro/The-Pre-Flight-Check/main/CLAUDE.mdgit clone --depth 1 https://github.com/mirekondro/The-Pre-Flight-CheckWrote 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/instructions/mirekondro/the-pre-flight-check/claude-md)<a href="https://agentmods.dev/instructions/mirekondro/the-pre-flight-check/claude-md"><img src="https://agentmods.dev/badge/instructions/mirekondro/the-pre-flight-check/claude-md/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/instructions/mirekondro/the-pre-flight-check/claude-md"><img src="https://agentmods.dev/badge/instructions/mirekondro/the-pre-flight-check/claude-md.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 | $0.01636 | $0.01636 |
| Opus 5 | $0.00818 | $0.00818 |
| Sonnet 5 | $0.00327 | $0.00327 |
| Haiku 4.5 | $0.00164 | $0.00164 |
Grade A, and why
The-Pre-Flight-Check CLAUDE.md 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 9d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — pre-flight-check repository
This file is loaded by Claude Code when contributors work on this repo itself. It's not the skill that ships to users — that lives in
skills/pre-flight-check/SKILL.md.
What this project is
pre-flight-check is a tool-neutral quality gate that ships as a native skill, rule, or instruction file for 10 AI coding agents. The engine is a single vanilla-Python script. The repo is the canonical source for the skill content, the adapter files, and the cross-platform installer.
Project philosophy — read before editing
The skill enforces these rules on users; this repo enforces them on itself:
| Rule | Why |
|---|---|
Zero runtime dependencies in run-pipeline.py |
The engine must install anywhere python3 runs. No pip install step. No supply-chain risk for users. |
Two-file skill content (SKILL.md + run-pipeline.py) |
Auditable in 5 minutes. Easy to fork. Easy to copy manually. |
| Auto-detect, never configure | If a heuristic is wrong, fix the heuristic, don't add a config knob. |
| Fail-fast, never paper over | The instruction files explicitly forbid agents from suppressing errors. Code changes that loosen this contract get rejected. |
| Structured output is load-bearing | The Markdown failure block format is part of the public contract. Any change to its shape is a breaking change — bump major. |
Full philosophy in CONTRIBUTING.md. If your change conflicts with one of these, it's probably the wrong change — but the conversation is welcome via issue.
Layout
.
├── skills/pre-flight-check/ # CANONICAL SKILL SOURCE
│ ├── SKILL.md # Agent contract (load-bearing)
│ └── scripts/run-pipeline.py # The pipeline engine (vanilla Python 3, no deps)
│
├── adapters/ # Per-tool instruction file sources
│ ├── cursor/pre-flight-check.mdc
│ ├── copilot/copilot-instructions.md
│ ├── windsurf/pre-flight-check.md
│ ├── cline/pre-flight-check.md
│ ├── kiro/pre-flight-check.md
│ ├── roo/pre-flight-check.md
│ └── README.md # Maintainer index — read when adding a new tool
│
├── AGENTS.md # Codex / generic AGENTS.md-based agents
├── GEMINI.md # Gemini CLI context file
├── gemini-extension.json # Gemini CLI extension manifest
│
├── .claude-plugin/ # Claude Code plugin marketplace manifest
│ ├── plugin.json
│ └── marketplace.json
│
├── install.sh / install.ps1 # Multi-tool installer (--tool flag, see --list-tools)
├── uninstall.sh # Thin wrapper around install.sh --uninstall
│
├── examples/ # Fixtures that double as docs and CI smoke targets
│ ├── node-broken/ # Rigged TS2345 failure
│ └── python-broken/ # Rigged mypy [return-value] failure
│
├── .github/workflows/ci.yml # ruff + mypy + shellcheck + PSScriptAnalyzer + fixture runs + installer round-trip
└── (README.md, INSTALL.md, CONTRIBUTING.md, LICENSE)
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.
- 9d ago First seen · 130 lines · 1,636 tokens per session scan A f0355eb305d4
The-Pre-Flight-Check CLAUDE.md is an instructions file published in the GitHub repository mirekondro/The-Pre-Flight-Check (2 stars, last pushed 2mo ago), licensed MIT. It adds 1,636 tokens to every session, about $0.0082 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 instructions, from other repositories
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.