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/codealive-ai/codealive-mcp/agents-mdgit clone --depth 1 https://github.com/CodeAlive-AI/codealive-mcpWhat 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 | $0.05329 | $0.05329 |
| Opus 5 | $0.02665 | $0.02665 |
| Sonnet 5 | $0.01066 | $0.01066 |
| Haiku 4.5 | $0.00533 | $0.00533 |
Grade A, and why
codealive-mcp 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 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.
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 — 423 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent instructions
Before editing or inspecting a target path, read every applicable
AGENTS.mdfrom the repository root through the target directory. Do not load instructions from unrelated subtrees.
This file provides guidance to coding agents working in this repository.
Version Control
- This repository uses jj. Before changing files, load
working-with-jjandcodealive-jj-development, stay in the current or assigned root, and use jj—not raw Git—for VCS mutations.
Development Commands
Installation and Setup
# Using uv (recommended)
uv venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
uv pip install -e .
# Using pip
python -m venv .venv
source .venv/bin/activate # On Windows: .venv\Scripts\activate
pip install -e .
Dependency Rules
- Keep Python dependency specifiers exact where this repository already pins them, including test extras and
build-system. - If
pyproject.tomlchanges affect resolved packages, verify the result through the lock/install path used by CI. - Do not introduce floating versions in CI or release automation when exact pins are practical.
- Do not adopt a versioned dependency, runtime, build tool, or GitHub Action until its release is more than seven days old. Keep
tool.uv.exclude-newer = "7 days"and audit release dates for non-Python tooling separately.
Running the MCP Server
# Basic run with stdio transport
python src/codealive_mcp_server.py
# With debug mode enabled
python src/codealive_mcp_server.py --debug
# With SSE transport
python src/codealive_mcp_server.py --transport sse --host 0.0.0.0 --port 8000
# With custom API key and base URL
python src/codealive_mcp_server.py --api-key YOUR_KEY --base-url https://custom.url
Docker Usage
# Build Docker image
docker build -t codealive-mcp .
# Run with Docker
docker run --rm -i -e CODEALIVE_API_KEY=your_key_here codealive-mcp
Testing
Quick Smoke Test
After making local changes, quickly verify everything works:
# Using make (recommended)
make smoke-test
# Or directly
python smoke_test.py
# With valid API key for full testing
CODEALIVE_API_KEY=your_key python smoke_test.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.
- yesterday First seen · 423 lines · 5,329 tokens per session scan A 23390d570e57
codealive-mcp AGENTS.md is an instructions file published in the GitHub repository CodeAlive-AI/codealive-mcp (88 stars, last pushed 16d ago), licensed MIT. It adds 5,329 tokens to every session, about $0.0266 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
edgequake AGENTS.md
Instructions for raphaelmansuy/edgequake, covering repository guidelines, project structure & module organization, build, test, and development commands, quick start with make and start with ollama (default).
awesome-copilot-id AGENTS.md
Instructions for GulajavaMinistudio/awesome-copilot-id, covering communication, explanation and documentation, markdown formatting, user communication style and workflow & methodology.
hiveshare CLAUDE.md
Instructions for KB-perByte/hiveshare, covering hiveshare — claude.md, repo layout, build & run, key env vars (server) and naming: hive vs memory.
llm-safe-haven CLAUDE.md
Instructions for pleasedodisturb/llm-safe-haven, covering llm safe haven, what this is, project structure, tdd — non-negotiable (adopted 2026-08-17) and the contract.
kleosrules AGENTS.md
Instructions for kleosr/kleosrules, a project described as: Cursor harness pack: user rules, skills, Bash hooks, local HANDOFF memory. macOS, Linux, Windows (WSL).
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.