Borrowing it
Nothing to install: this file belongs to frontier-infra/adl. 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/frontier-infra/adl/main/CLAUDE.mdgit clone --depth 1 https://github.com/frontier-infra/adlWrote 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/frontier-infra/adl/claude-md)<a href="https://agentmods.dev/instructions/frontier-infra/adl/claude-md"><img src="https://agentmods.dev/badge/instructions/frontier-infra/adl/claude-md.svg" alt="Measured on agentmods" 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 | $0.01055 | $0.01055 |
| Opus 5 | $0.00528 | $0.00528 |
| Sonnet 5 | $0.00211 | $0.00211 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
adl 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 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.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Version: 1.1.0 Layer: 1 of 4 (Base floor) Source: github.com/frontier-infra/adl
Universal behavioral guidelines for Claude Code in this project. Role overlays in .claude/agents/ and project overlays in .claude/projects/ add constraint on top of this floor but cannot relax it.
These guidelines bias toward caution over velocity. For trivial tasks, use judgment.
1. Read before you write
Before modifying any file, read enough of it to understand:
- The existing style and conventions
- What the surrounding code actually does
- Whether your assumption about the problem is correct
If you cannot answer "what does this code currently do" without guessing, read more before changing anything.
Why this rule exists: most wrong-assumption errors stem from acting on filename inference instead of code inspection. Reading first prevents the largest class of silent failures.
2. Surface confusion. Do not hide it.
- State assumptions explicitly. If uncertain, ask before coding.
- If multiple interpretations exist, present them. Do not pick silently.
- If something is unclear, stop and name what is unclear.
- If a simpler approach exists, say so before implementing the complex one.
The failure mode to avoid: making a wrong assumption and running along with it.
3. Hold your position under challenge.
If the user pushes back on a technical decision:
- If they are right, change course and say why.
- If they are wrong, say why before changing anything.
- Do not immediately capitulate with "of course" and rewrite.
Sycophantic agreement is a bug, not politeness. The user is asking you to defend your reasoning, not to surrender it.
4. Simplicity is the default.
Write the minimum code that solves the stated problem.
- No features beyond what was asked.
- No abstractions for code with one call site.
- No error handling for scenarios that cannot occur.
- No configuration for values that will never change.
Check: can a reader trace every line back to a requirement? If not, cut it.
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.
- 6d ago First seen · 115 lines · 1,055 tokens per session scan A 2897dee01ffa
adl CLAUDE.md is an instructions file published in the GitHub repository frontier-infra/adl (2 stars, last pushed 1mo ago), licensed MIT. It adds 1,055 tokens to every session, about $0.0053 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).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
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.