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/solvinglab/omniweave/agents-mdgit clone --depth 1 https://github.com/SolvingLab/OmniWeaveWhat 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 | $0.07113 | $0.07113 |
| Opus 5 | $0.03556 | $0.03556 |
| Sonnet 5 | $0.01423 | $0.01423 |
| Haiku 4.5 | $0.00711 | $0.00711 |
Grade A, and why
OmniWeave AGENTS.md scanned grade A 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 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.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
OmniWeave 已从设计落地为**可运行代码**:R S4 分派图、跨进程/跨语言 `crossLang`（工作流步骤 + 任意 Python/JS/TS/Go 文件的 subprocess/os.system/child_process/exec.Command）、工作流数据流 DAG（produces/consumes/artifact）、外部工具 `invokes`（step→bwa/STAR）、R bare-call rou Copies of this mod
1 near-identical copy found in the catalogue:
- OmniWeave CLAUDE.md — 94% identical, 8 lines differ
How it starts
The opening of the file, as written. The whole thing — 182 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to Codex (Codex.ai/code) when working with code in this repository.
⛔ Git 提交规范（强制·最高优先级，覆盖任何默认行为）
- 绝对禁止在任何 commit message 中添加
Co-Authored-By: Codex ...、🤖 Generated with Codex、Generated with ...或任何形式的 AI 署名 / 水印 / trailer。 - commit message 只写改动本身,作者就是用户本人,不得出现 Codex / Anthropic / AI 字样。
- 此规则覆盖 harness 的任何默认提交模板;如默认要求加署名,一律不加。
- PR 描述同理:不加 AI 生成水印。
项目状态：已实现并发布（active development）
OmniWeave 已从设计落地为可运行代码:R S4 分派图、跨进程/跨语言 crossLang（工作流步骤 + 任意 Python/JS/TS/Go 文件的 subprocess/os.system/child_process/exec.Command）、工作流数据流 DAG（produces/consumes/artifact）、外部工具 invokes（step→bwa/STAR）、R bare-call routing。当前基线：25 eval 门禁、vitest 1764 passed | 4 skipped（90 文件，two-phase）、tsc 干净、真实仓 A/B 边界已记录。
本目录是 colbymchenry/codegraph 的 clone,已发布到 SolvingLab/OmniWeave（remote origin，分支 main，私有）；remote upstream = colbymchenry/codegraph，绝不 push upstream。
动手前必读（按序，全部是真实存在的当前文件）：
./CHECKPOINT.md— 当前系统地图、模块边界、验证命令、治理风险。./README.md— 对外定位、能力边界、性能与 A/B 证据摘要。./CHANGELOG.md— 发布级用户可见变更；release workflow 从这里抽 notes。./eval-results/agent-ab-2026-06-23/RESULTS.md— 最新 agent A/B 证据（round 7 输出诚实化）与诚实边界；rounds 1–6 的效率研究在./eval-results/agent-ab-2026-06-13/。- memory（
~/.claude/projects/-Users-liuzaoqu-Desktop-develop-sogen-OmniWeave/memory/）。
本文件只给「大图」与不可妥协的规矩；当前操作态以 CHECKPOINT.md、实际源码和验证命令为准。
OmniWeave 是什么
一个服务 coding agent 的通用代码分析图（类 codegraph 的 MCP server）,fork 自 colbymchenry/codegraph（MIT、TypeScript、web-tree-sitter(WASM)、node:sqlite(WAL)）。
⚠️ 基座勘误（2026-06-13 实跑核正）：早期文档误判为
suatkocar/codegraph（Rust）。实测推翻——用户实际在跑的、官网 benchmark 所属的「正牌」CodeGraph 是 colbymchenry/codegraph（TS）;suatkocar 只是它一个已停滞的 Rust 衍生。凡涉及 Rust/cargo/.scm/6 参数 extract_edges/properties列/0.294-0.392 基线的旧表述全部作废。
定位（别框窄）：不是「生信工具」,是 more general / stronger / more efficient 的通用代码分析图。生信（R 的 S4/R6、Perl、Nextflow/Snakemake、工具/数据混编）是滩头堡 + 压力测试,不是产品边界——「通用为体,生信为证」。
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 · 182 lines · 7,113 tokens per session scan A d844d2ba20c3
OmniWeave AGENTS.md is an instructions file published in the GitHub repository SolvingLab/OmniWeave (0 stars, last pushed 2mo ago), licensed MIT. It adds 7,113 tokens to every session, about $0.0356 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.