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/knitli/codeweaver/agents-mdgit clone --depth 1 https://github.com/knitli/codeweaverWhat 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 | $0.08010 | $0.08010 |
| Opus 5 | $0.04005 | $0.04005 |
| Sonnet 5 | $0.01602 | $0.01602 |
| Haiku 4.5 | $0.00801 | $0.00801 |
Grade A, and why
codeweaver AGENTS.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.
How it starts
The opening of the file, as written. The whole thing — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Claude Code (claude.ai/code), Github Copilot, Roo, and other AI agents when working with code in this repository.
Project Overview
CodeWeaver is an extensible MCP (Model Context Protocol) server for semantic code search. It provides intelligent codebase context discovery through a single find_code tool interface, supporting multiple embedding providers, vector databases, and data sources through a plugin architecture.
Architecture: CodeWeaver runs as a daemon with separate transport servers:
- Daemon: Background services (indexing, file watching, health monitoring)
- Management Server: HTTP endpoints at port 9329 (health, status, metrics)
- MCP HTTP Server: FastMCP at port 9328 for HTTP clients
- MCP stdio: Lightweight proxy that forwards to the HTTP backend (default transport)
Current Status: Early release (0.x). Most core features complete and relatively stable. Advanced functionality planned in several epics.
[!IMPORTANT] Because it is an MCP server, you can use CodeWeaver while assisting with CodeWeaver development! In your list of available tools, you may see
find_codeorcodeweaver__find_codeCongrats! You're both an early tester and contributor!
Project Constitution (DEFINITIVE GUIDANCE)
This project is governed by the CodeWeaver Constitution at .specify/memory/constitution.md. (path relative to repo root)
All development decisions, code reviews, and technical choices MUST comply with the constitutional principles. When in doubt, consult the constitution first.
Constitutional Requirements Summary
- AI-First Context: Enhance AI agent understanding of code through precise context delivery
- Proven Patterns: Use FastAPI/pydantic ecosystem patterns over reinvention
- Evidence-Based Development (NON-NEGOTIABLE): All decisions backed by verifiable evidence
- Testing Philosophy: Effectiveness over coverage - focus on user-affecting behavior, likely user stories and usage
- Simplicity Through Architecture: Clear, flat structure with obvious purpose
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 · 679 lines · 8,010 tokens per session scan A 257e594f64d4
codeweaver AGENTS.md is an instructions file published in the GitHub repository knitli/codeweaver (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 8,010 tokens to every session, about $0.0401 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 2026-08-30.
Other instructions, from other repositories
claude-code-templates CLAUDE.md
Claude Code instructions for davila7/claude-code-templates, covering claude.md, project overview, essential commands, development and component catalog.
kubb AGENTS.md
Instructions for kubb-labs/kubb, covering agents.md, high-level architecture, project structure and commands, repository setup and plugin ecosystem.
figwright CLAUDE.md
Instructions for awdr74100/figwright: Read AGENTS.md first — it's the single source of guidance for this repo: architecture, layout, tech stack, commands, conventions, release flow, and gotchas.
kessoku AGENTS.md
Instructions for mazrean/kessoku, covering repository guidelines — kessoku, project structure, common commands, build and test.
ClawAI CLAUDE.md
Instructions for ihabkhaled/ClawAI, covering clawai — root policy, identity, authority hierarchy (higher wins on conflict), first command, always and work arriving as a document.
Claude-PHP-SDK copilot-instructions.md
Instructions for claude-php/Claude-PHP-SDK, covering copilot instructions for claude php sdk, project goals, architecture & core components, directory structure (to be created) and key architectural patterns.