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/intelligent-internet/commonground/agents-mdgit clone --depth 1 https://github.com/Intelligent-Internet/CommonGroundWrote 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/intelligent-internet/commonground/agents-md)<a href="https://agentmods.dev/instructions/intelligent-internet/commonground/agents-md"><img src="https://agentmods.dev/badge/instructions/intelligent-internet/commonground/agents-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 | $0.00925 | $0.00925 |
| Opus 5 | $0.00463 | $0.00463 |
| Sonnet 5 | $0.00185 | $0.00185 |
| Haiku 4.5 | $0.00093 | $0.00093 |
Grade A, and why
CommonGround 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 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Repository Role
CommonGround/ is the active implementation repository for CommonGround.
Primary implementation paths:
CommonGround/: kernel, truth, service, SDK, and CLI code.Integrations/nanobot/: external runtime, provision, and leaf worker integration.tests/: regression coverage and executable contracts.docs/: current architecture and design documentation.
Documentation Priority
When working in this repository, read these documents first:
docs/en/01-constitution.mdordocs/zh/01-constitution.mddocs/en/02-three-plane-model.mdordocs/zh/02-three-plane-model.mddocs/en/03-design-review-principles.mdordocs/zh/03-design-review-principles.mddocs/en/introduction/ordocs/zh/introduction/
The English and Chinese documentation trees are parallel current surfaces. Background material can explain design history, but it does not override the current docs or code.
Code Structure
Important paths:
CommonGround/contracts/CommonGround/kernel/CommonGround/infra/CommonGround/sdk/CommonGround/adapters/CommonGround/service/Integrations/nanobot/tests/
Common Commands
Setup:
git submodule update --init --recursive
uv sync
Reset the database:
PG_DSN=postgresql://USER:PASSWORD@HOST:PORT/DBNAME uv run -m scripts.setup.reset_db
Run the service:
PG_DSN=postgresql://USER:PASSWORD@HOST:PORT/DBNAME uv run cg service run
Compile check:
uv run python -m compileall CommonGround Integrations tests
Full tests:
PG_DSN=postgresql://USER:PASSWORD@HOST:PORT/DBNAME uv run --with pytest python -m pytest tests -q
Focused mainline tests:
uv run --with pytest python -m pytest tests/test_agent_only_service.py tests/test_cg_cli.py tests/test_leaf_worker_main.py tests/test_nanobot_bridge.py -q
Testing Notes
The pytest configuration creates isolated test databases per worker and resets each database per test. Parallel file execution should be safe when tests use tests/conftest.py and tests/pg_support.py.
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 · 115 lines · 925 tokens per session scan A 876029150e47
CommonGround AGENTS.md is an instructions file published in the GitHub repository Intelligent-Internet/CommonGround (149 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 925 tokens to every session, about $0.0046 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
playbooks CLAUDE.md
Instructions for playbooks-ai/playbooks, covering claude.md, project overview, core architecture, framework components and key architectural insights.
agent-claim-network AGENTS.md
Instructions for FTShare-Lab/agent-claim-network, covering agents.md, 项目概览, 当前架构, rust 规范 and 数据与安全边界.
orchestra CLAUDE.md
Instructions for aleksbuss/orchestra, covering orchestra swarm engine, 🤖 system prompt for ai assistants, level 1 (this file) holds only, level 2 (docs/references/) holds and when you are asked to record something here.
agent-claim-network CLAUDE.md
Instructions for FTShare-Lab/agent-claim-network, a project described as: 面向终端的通用 AI 助手,让 Agent 之间共享可检索、可追溯且允许分歧的知识。让下一次判断,带着来源出发。.
Termite-Protocol CLAUDE.md
Claude Code instructions for billbai-longarena/Termite-Protocol, covering termite protocol — source repository, terminology (权威术语表), repository map, current state and known issues.
ai-dial-core CLAUDE.md
Claude Code instructions for epam/ai-dial-core, covering claude.md, build & run, set credentials via environment variables, build (skip tests) and run all tests.