Borrowing it
Nothing to install: this file belongs to anzellai/sky. 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/anzellai/sky/main/CLAUDE.mdgit clone --depth 1 https://github.com/anzellai/skyWrote 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/anzellai/sky/claude-md)<a href="https://agentmods.dev/instructions/anzellai/sky/claude-md"><img src="https://agentmods.dev/badge/instructions/anzellai/sky/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/anzellai/sky/claude-md"><img src="https://agentmods.dev/badge/instructions/anzellai/sky/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 | $0.11057 | $0.11057 |
| Opus 5.5 | $0.04423 | $0.04423 |
| Sonnet 5.5 | $0.02211 | $0.02211 |
| Haiku 4.5 | $0.01106 | $0.01106 |
Grade A, and why
sky 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 5d 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 — 880 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Entry point for Claude Code in the Sky repository. The agent-agnostic source of truth is AGENTS.md (imported below) — it teaches the language, the app-building decisions, the stdlib (via
sky doc), build & test, and the non-negotiable code rules for any AI tool. This file adds only the Claude-Code-specific operational rules that do not apply to other agents: the autonomous-loop protocol, mem-guard, and background-task hygiene.Read AGENTS.md first. Then the rules below govern how Claude Code operates when driving multi-step / autonomous work in this repo.
Response style (INVIOLABLE)
Every response to the user, and every agent report, follows these rules.
- Write in ASD-STE100 Simplified Technical English. Keep each sentence short. Put one idea in each sentence. Use the active voice. Use the present tense where you can. Use common, approved words.
- Use British English spelling. For example, write behaviour, colour, organise, licence, and whilst.
- Use plain punctuation. Do not use em-dashes, en-dashes, semicolons, or emoji. Use full stops and commas.
- Do not use filler or marketing words. For example, do not write robust, seamless, leverage, delve, comprehensive, powerful, or effortless. State the fact plainly.
This rule governs prose in chat and in reports. It does not change code, code comments, identifiers, or quoted output.
@AGENTS.md
Claude Code — operational rules
These are Claude-Code-specific. They sit on top of AGENTS.md's engineering norms
(no-deferral, regression-test-first, timeout-bounding, disk hygiene, template +
doc sync) — which apply to every agent — and add the loop/session mechanics that
are specific to Claude Code's tools (/loop, Judge/Architect agents, the
Workflow tool, ScheduleWakeup, Monitor, the file-based memory).
Private context — the .private.md convention (INVIOLABLE)
No private context ever enters a commit. A private app name, a private path, a client name, a secret, an internal URL, a sensitive constraint — none of it belongs in any file this repo tracks (a committed doc, a goal file, a fixture, a test, a comment, a commit message). Yet the context must not be LOST: I still need it across compactions and new sessions.
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.
- 5d ago Changed · -11 lines · -43 tokens per session 74b9b194b386
- 10d ago Changed · +27 lines · +415 tokens per session d452320503b5
- 14d ago Changed · +3 lines · +59 tokens per session ec102efd6102
- 1mo ago Changed · +1 lines · +24 tokens per session 12928d9a1090
- 1mo ago Changed · +11 lines · +176 tokens per session 88d025bc7407
- 1mo ago Changed · -5 tokens per session 298a09c5147e
- 1mo ago Changed · +16 lines · +287 tokens per session 0ff141391587
- 1mo ago Changed · +23 lines · +363 tokens per session c77a9072fc36
- 1mo ago Changed · +39 lines · +565 tokens per session 5889512e3306
- 1mo ago First seen · 771 lines · 9,216 tokens per session scan A 9557c0facfdf
sky CLAUDE.md is an instructions file published in the GitHub repository anzellai/sky (438 stars, last pushed yesterday), licensed Apache-2.0. It adds 11,057 tokens to every session, about $0.0442 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.
sky CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sky CLAUDE.mdanzellai/sky | Instructions file | 438 | yesterday | Apache-2.0 | A | 11,057 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | today | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |