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/entity12208/codellm/claude-mdgit clone --depth 1 https://github.com/entity12208/CodeLLMWhat 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 | $0.00304 | $0.00304 |
| Opus 5 | $0.00152 | $0.00152 |
| Sonnet 5 | $0.00061 | $0.00061 |
| Haiku 4.5 | $0.00030 | $0.00030 |
Grade A, and why
CodeLLM 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 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.
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.
What it actually says
CodeLLM
Advanced AI coding agent built from scratch in TypeScript.
Architecture
src/
agent/ # Core agent: Agent (orchestrator), AgentLoop (conversation loop)
providers/ # LLM providers: Anthropic, OpenAI (abstract Provider interface)
tools/ # Tool system: Tool interface, Registry, Executor, implementations
context/ # Context management: ContextManager, Compactor, SystemPrompt
permissions/ # Permission system: PermissionManager with rules
session/ # Session persistence and history
ui/ # Terminal UI: Terminal, Spinner, ToolRenderer
config/ # Configuration loading and types
utils/ # Shared utilities
Build & Run
npm install
npm run build # TypeScript compile
npm run dev # Run in dev mode (tsx)
npm start # Run compiled version
Key Design Decisions
- Multi-provider: Abstract Provider interface supports Anthropic and OpenAI-compatible APIs
- Pure Node.js: No React/Ink — clean readline + ANSI for terminal UI
- Event-driven agent loop: AsyncGenerator yields events, caller decides rendering
- Composable tools: Tools are plain objects implementing a clean interface
- Smart compaction: Uses the LLM itself to summarize older conversation turns
- Concurrent tool execution: Read-only tools run in parallel automatically
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 First seen · 37 lines · 304 tokens per session scan A 3aef5b376c4a
CodeLLM CLAUDE.md is an instructions file published in the GitHub repository entity12208/CodeLLM (2 stars, last pushed 5mo ago), licensed MIT. It adds 304 tokens to every session, about $0.0015 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
moss AGENTS.md
Instructions for D-Robotics/moss, covering agents.md, 仓库身份, 文档所有权与阅读顺序, 代码规范执行摘要（必须遵守） and 第一次进入仓库.
hana-developer-cli-tool-example mcp-server-development.instructions.md
Use when creating or updating MCP (Model Context Protocol) server components. Enforces TypeScript patterns, JSON-RPC communication rules, tool/resource/prompt registration, and integration with CLI command metadata. Ensures MCP server follows protocol requirements and maintains consistency with the CLI infrastructure.
Agents-for-js copilot-instructions.md
Instructions for microsoft/Agents-for-js, covering copilot instructions for microsoft/agents-for-js, commands, architecture (the big picture) and conventions.
mirage CLAUDE.md
Claude Code instructions for strukto-ai/mirage, covering claude.md, repo layout, typescript packages, python/typescript parity and module layout.
dynatrace-mcp copilot-instructions.md
Instructions for dynatrace-oss/dynatrace-mcp, covering dynatrace mcp server, guidelines, repo structure, coding guidelines and dependencies.
dynatrace-mcp typescript.instructions.md
Instructions for dynatrace-oss/dynatrace-mcp, covering mcp server – typescript agent instructions, reference documentation, project-specific patterns, console.error for logging and implementing mcp tools.