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/the-open-agent/openagent/claude-mdgit clone --depth 1 https://github.com/the-open-agent/openagentWrote 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/the-open-agent/openagent/claude-md)<a href="https://agentmods.dev/instructions/the-open-agent/openagent/claude-md"><img src="https://agentmods.dev/badge/instructions/the-open-agent/openagent/claude-md.svg" alt="Measured on agentmods" 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 | $0.01049 | $0.01049 |
| Opus 5 | $0.00524 | $0.00524 |
| Sonnet 5 | $0.00210 | $0.00210 |
| Haiku 4.5 | $0.00105 | $0.00105 |
Grade A, and why
openagent 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 4d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Commands
Backend (Go)
go build # build backend binary
go run main.go # run backend (port 14000)
go test ./... # run all tests
go test ./object/... -run TestFoo # run a single test
Frontend (React)
cd web && yarn install
yarn start # dev server on port 13001
yarn build # production build (output goes to web/build, then copied to static/)
yarn lint:js # lint JS
Full production build uses build.sh which cross-compiles for linux/amd64, linux/arm64, linux/riscv64.
Backend serves the frontend as embedded static files (embed.go); during development the frontend proxy is configured to hit localhost:14000.
Architecture
Backend (Go / Beego)
Module: github.com/the-open-agent/openagent
The backend is a standard Beego MVC app. Every entity follows the same three-layer pattern:
-
object/<entity>.go— struct definition (xorm tags for DB), and all DB access functions:GetGlobal<Entities>,Get<Entity>Count,GetPagination<Entities>,Get<Entity>,Add<Entity>,Update<Entity>,Delete<Entity>. The primary key is always(Owner string, Name string). Useutil.GetId(owner, name)/util.GetOwnerAndNameFromIdWithError(id)for composite key serialization. -
controllers/<entity>.go— Beego controller methods wired to routes. Standard set:GetGlobal<Entities>,Get<Entities>,Get<Entity>,Add<Entity>,Update<Entity>,Delete<Entity>. Usec.IsAdmin()/c.IsGlobalAdmin()/c.RequireSignedIn()for auth. Paginated list APIs acceptp,pageSize,field,value,sortField,sortOrderquery params and usepagination.SetPaginator. -
routers/router.go—beego.Routercalls grouped by entity (all routes for the same entity's CRUD kept together). No alphabetical ordering within a group. New entity routes should be inserted next to their entity's existing routes (not appended to the end of the file).
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.
- 4d ago First seen · 66 lines · 1,049 tokens per session scan A 7f03b4a36e27
openagent CLAUDE.md is an instructions file published in the GitHub repository the-open-agent/openagent (5,599 stars, last pushed today), licensed Apache-2.0. It adds 1,049 tokens to every session, about $0.0052 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
AstrBot AGENTS.md
AGENTS.md instructions for AstrBotDevs/AstrBot, covering setup commands, core, dashboard(webui), pre-commit setup and dev environment tips.
AstrBot copilot-instructions.md
Copilot instructions for AstrBotDevs/AstrBot, covering astrbot development instructions, working effectively, bootstrap and install dependencies, running the application and dashboard build (vue.js/node.js).
gptme AGENTS.md
AGENTS.md instructions for gptme/gptme, covering agent instructions for gptme, git workflow, code style, testing and project structure.
lobehub AGENTS.md
AGENTS.md instructions for lobehub/lobehub, covering lobehub development guidelines, tech stack, agent skills, project structure and spa routes and features.
lobehub GEMINI.md
Gemini CLI instructions for lobehub/lobehub: Please follow instructions @./AGENTS.md.
lobehub CLAUDE.md
Claude Code instructions for lobehub/lobehub, a project described as: 🤯 LobeHub is your Chief Agent Operator, organizing your agents into 7×24 operations by hiring, scheduling, and reporting on your entire AI team.