Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add instructions/graycodeai/starling/claude-mdgit clone --depth 1 https://github.com/GrayCodeAI/starlingWhat 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 | $0.00727 | $0.00727 |
| Opus 5 | $0.00364 | $0.00364 |
| Sonnet 5 | $0.00145 | $0.00145 |
| Haiku 4.5 | $0.00073 | $0.00073 |
Grade A, and why
starling 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 yesterday.
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.
This is a copy
80% identical to tabularis AGENTS.md — 21 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
GitNexus — Code Intelligence
This project is indexed by GitNexus as starling (210621 symbols, 225507 relationships, 136 execution flows). Use the GitNexus MCP tools to understand code, assess impact, and navigate safely.
Index stale? Run
node .gitnexus/run.cjs analyzefrom the project root — it auto-selects an available runner. No.gitnexus/run.cjsyet?npx gitnexus analyze(npm 11 crash →npm i -g gitnexus; #1939).
Always Do
- MUST run impact analysis before editing any symbol. Before modifying a function, class, or method, run
impact({target: "symbolName", direction: "upstream"})and report the blast radius (direct callers, affected processes, risk level) to the user. - MUST run
detect_changes()before committing to verify your changes only affect expected symbols and execution flows. For regression review, compare against the default branch:detect_changes({scope: "compare", base_ref: "main"}). - MUST warn the user if impact analysis returns HIGH or CRITICAL risk before proceeding with edits.
- When exploring unfamiliar code, use
query({search_query: "concept"})to find execution flows instead of grepping. It returns process-grouped results ranked by relevance. - When you need full context on a specific symbol — callers, callees, which execution flows it participates in — use
context({name: "symbolName"}). - For security review,
explain({target: "fileOrSymbol"})lists taint findings (source→sink flows; needsanalyze --pdg).
Never Do
- NEVER edit a function, class, or method without first running
impacton it. - NEVER ignore HIGH or CRITICAL risk warnings from impact analysis.
- NEVER rename symbols with find-and-replace — use
renamewhich understands the call graph. - NEVER commit changes without running
detect_changes()to check affected scope.
Resources
| Resource | Use for |
|---|---|
gitnexus://repo/starling/context |
Codebase overview, check index freshness |
gitnexus://repo/starling/clusters |
All functional areas |
gitnexus://repo/starling/processes |
All execution flows |
gitnexus://repo/starling/process/{name} |
Step-by-step execution trace |
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.
- yesterday First seen · 45 lines · 727 tokens per session scan A 8b164f5fab46
starling CLAUDE.md is an instructions file published in the GitHub repository GrayCodeAI/starling (2 stars, last pushed 2d ago), licensed MIT. It adds 727 tokens to every session, about $0.0036 per session on Opus 5. A static security scan graded it A with 0 findings. It is 80% identical to tabularis AGENTS.md, differing in 21 lines, and is treated as a copy.
Other instructions, from other repositories
cocoindex-code CLAUDE.md
Instructions for cocoindex-io/cocoindex-code, covering claude.md, build and test commands, architecture, process model and key layers.
mainbranch AGENTS.md
Instructions for noontide-co/mainbranch, covering agent instructions, product shape, daily operating loop, quick start and repository layout.
mainbranch CLAUDE.md
Instructions for noontide-co/mainbranch, covering claude code instructions, repository role, product loop to preserve, how to work here and engine vs business repo.
docpull AGENTS.md
Instructions for raintree-technology/docpull: DocPull is the open-source context dependency manager for AI agents. Its core contract is local-first, browser-free by default, reproducible, cited, and budget guarded.
vkr-builder CLAUDE.md
Instructions for maxbarsukov/vkr-builder, covering vkr-builder, как себя вести and основные команды.
mini-claude-code-python AGENTS.md
Instructions for Xiaxia1997/mini-claude-code-python, covering mini claude code python 协作规则, 项目目标, 默认语言与风格, 代码来源边界 and 章节一致性要求.