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/AGENTS.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/agents-md)<a href="https://agentmods.dev/instructions/anzellai/sky/agents-md"><img src="https://agentmods.dev/badge/instructions/anzellai/sky/agents-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/agents-md"><img src="https://agentmods.dev/badge/instructions/anzellai/sky/agents-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 | $0.26327 | $0.26327 |
| Opus 5.5 | $0.10531 | $0.10531 |
| Sonnet 5.5 | $0.05265 | $0.05265 |
| Haiku 4.5 | $0.02633 | $0.02633 |
Grade C, and why
sky AGENTS.md scanned grade C with 1 finding 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 2d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
builds clean from a wiped slate (`rm -rf sky-out .skycache .skydeps && sky How it starts
The opening of the file, as written. The whole thing — 1,032 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Agent-agnostic guide for AI tools (Claude, Copilot, Cursor, Codex, …) working in the Sky repository. It is the source of truth; tool-specific files layer on top of it (Claude Code reads
CLAUDE.md, which imports this file and adds Claude-Code-only operational rules).Progressive disclosure. This file is deliberately lean. It teaches the language, the app-building decisions, and the non-negotiable rules, then points you at two authoritative, always-current sources for depth:
sky doc <Module>— the live stdlib API (typed signatures + summaries + examples), generated from the stdlib source, so it never drifts. Prefer it over any hand-copied API table.sky doc --listenumerates every module;sky doc --serveopens a browsable server.docs/— deep dives (architecture, Sky.Live, Std.Db, Std.Ui, auth, tooling). The map is in the Deep dives table below.
What Sky is
Sky is an Elm-family, purely-functional language that compiles to typed Go. One language for the whole stack: web UIs (Sky.Live), HTTP/JSON APIs, CLIs, TUIs, desktop apps, background jobs. The design goal is "if it compiles, it works" — no user-written FFI, no nulls, no silent wrong answers, and no runtime panic from well-typed code, clear errors, batteries-included stdlib.
The one honest carve-out: partial arithmetic primitives fail LOUDLY, never
silently. A well-typed 10.0 / 0.0 has no answer Sky can represent (there is
no Inf/NaN shape), so it raises a classified DivisionByZero — recovered
per-request to a 500 in a server, or exit(1) + a structured log in a CLI — and
is caught by the whole-app panic net (docs/architecture/sky-stdlib-correctness.md
§2.9; classifyPanic in runtime-go/rt/panic_recover.go names the eleven panic
classes). It is never a silent wrong value (integer ///% by zero are total
and return 0, matching Elm). Json.Encode.encode of a NaN or infinite Float
fails the same way, as a classified JsonEncodeFailure, never an empty
string, and Decimal.toInt / toMinor / Money.toMinor past the 64-bit Int
range (or Decimal.toFloat past the Float range) fails as a classified
NumericOverflow, never a wrapped number. Code that divides by a value it does not control should zero-guard the
divisor; a fallible Maybe-returning division is an offered convenience, not a
soundness requirement. "No runtime panic" therefore means no UNCLASSIFIED panic and no
silent corruption — the property a service actually needs.
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.
- 2d ago Changed · +23 lines · +620 tokens per session 08783c93d826
- 4d ago Changed · +16 lines · +609 tokens per session 446071a8f00a
- 5d ago Changed · -54 lines · +182 tokens per session b6b679a53a2c
- 8d ago Changed · +21 lines · +4,133 tokens per session aa5baae52fc2
- 11d ago Changed · +101 tokens per session fc96aef5db92
- 14d ago Changed · +15 lines · +311 tokens per session c5f026a8233e
- 21d ago Changed · +43 lines · +843 tokens per session 0cefcd564628
- 1mo ago Changed · +6 lines · +121 tokens per session d78c27fdb4d3
- 1mo ago Changed · +10 lines · +199 tokens per session 282b8cb458bc
- 1mo ago First seen · 952 lines · 19,208 tokens per session scan C 0aa2bee13f01
sky AGENTS.md is an instructions file published in the GitHub repository anzellai/sky (438 stars, last pushed yesterday), licensed Apache-2.0. It adds 26,327 tokens to every session, about $0.1053 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
sky AGENTS.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| sky AGENTS.mdanzellai/sky | Instructions file | 438 | yesterday | Apache-2.0 | C | 26,327 | Codex, OpenCode |
| 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 |