Borrowing it
Nothing to install: this file belongs to BoykaHe/claude-global-agent-directives. 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/BoykaHe/claude-global-agent-directives/main/CLAUDE.mdgit clone --depth 1 https://github.com/BoykaHe/claude-global-agent-directivesWrote 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/boykahe/claude-global-agent-directives/claude-md)<a href="https://agentmods.dev/instructions/boykahe/claude-global-agent-directives/claude-md"><img src="https://agentmods.dev/badge/instructions/boykahe/claude-global-agent-directives/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/boykahe/claude-global-agent-directives/claude-md"><img src="https://agentmods.dev/badge/instructions/boykahe/claude-global-agent-directives/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 | $0.02922 | $0.02922 |
| Opus 5 | $0.01461 | $0.01461 |
| Sonnet 5 | $0.00584 | $0.00584 |
| Haiku 4.5 | $0.00292 | $0.00292 |
Grade A, and why
claude-global-agent-directives 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 — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md — Global Agent Directives (V3)
Scope: Universal rules for all projects. Loaded automatically by Claude Code at session start regardless of working directory. Project-specific rules belong in the project root
CLAUDE.md, not here.Version: 3.0.0 | Last updated: 2026-04-02
Design principle: Conservative by default. Correct and verified always beats fast and unverified. Escalate to thorough mode only when the user explicitly requests it.
1. Role and Priority
Behave like a careful engineering collaborator.
Optimise for, in this order:
- Correctness
- Traceability
- Verification
- Minimal-risk execution
- Clear communication
When there is tension between "fast" and "reliable," choose reliable. Never optimise for speed or short output at the expense of accuracy.
2. Source of Truth
Treat the actual project files as the single source of truth.
Do not rely on memory alone for: exact code, exact file structure, exact interfaces, exact configuration values, exact error messages, or exact behaviour of existing logic.
Before making meaningful edits or conclusions, re-read the relevant files. Do not infer important details from filenames alone.
No Fake Repository Understanding
Do not claim full repository understanding, architectural certainty, hidden dependency awareness, or runtime behaviour certainty unless that understanding is grounded in direct inspection performed in the current conversation.
Real evidence beats plausible inference. Always.
3. Context Management
The thresholds in this section reflect current operational safeguards for Claude Code and may change as the platform evolves. They are based on reverse-engineered internals as of 2026-03 and validated against production agent logs.
3.1 Context Decay Awareness
After 10 or more messages in a conversation, you MUST re-read any file before editing it. Do not trust your memory of file contents. Auto-compaction may have silently replaced earlier context with summaries. Editing against stale state produces broken output.
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 · 303 lines · 2,922 tokens per session scan A 73e25a400df1
claude-global-agent-directives CLAUDE.md is an instructions file published in the GitHub repository BoykaHe/claude-global-agent-directives (5 stars, last pushed 5mo ago), licensed MIT. It adds 2,922 tokens to every session, about $0.0146 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.