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/mabelisle/omni-cli/agents-mdgit clone --depth 1 https://github.com/mabelisle/omni-cliWhat 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 | $0.05037 | $0.05037 |
| Opus 5 | $0.02518 | $0.02518 |
| Sonnet 5 | $0.01007 | $0.01007 |
| Haiku 4.5 | $0.00504 | $0.00504 |
Grade A, and why
omni-cli 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 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:8000/v1/chat/completions \ How it starts
The opening of the file, as written. The whole thing — 739 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md - Omni-CLI Repository Guidelines
This file provides guidance for AI coding agents working on the Omni-CLI project.
📦 Project Structure
Core Files
- Dockerfile - Multi-stage build (base → builder → final) with Node.js 25-slim
- entrypoint.sh - Container initialization (UID/GID mapping, SSH keys, volume ownership, API server startup)
- omni-cli.sh - Menu-driven interactive CLI interface (main user-facing script)
- omni-env.sh - Environment variable setup for npm and Node.js
- api.js - OpenAI-compatible API server for Codex/Gemini passthrough
- src/sync_openrouter_models.py - Python utility to sync OpenRouter models into OpenCode config
- .gitlab-ci.yml - GitLab Auto-DevOps configuration
- README.md - User-facing documentation
Configuration Directories (mounted volumes)
/data- Workspace storage (projects, repos)/config- Tool configs (npm cache, CLI auth tokens)/config/gemini- Gemini CLI config/config/codex- Codex CLI config/config/copilot- Copilot CLI config/config/claude- Claude CLI config/config/npm- Global npm packages and cache/config/opencode- OpenCode config, data, cache
Installed CLI Tools (in container)
@google/gemini-cli- Gemini CLI@openai/codex- OpenAI Codex CLI@github/copilot- GitHub Copilot CLI@anthropic-ai/claude-code- Anthropic Claude CLIopencode-ai- OpenCode CLI
🛠️ Build, Lint, and Test Commands
Build Commands
# Build the Docker image locally
docker build -t omni-cli .
# Build with custom version tag
docker build -t omni-cli:latest --build-arg OMNI_CLI_VERSION=v1.0.0 .
# Build with custom SSH password
docker build -t omni-cli --build-arg USER_PASS=newpassword .
Run Commands
# Run with Docker Compose (recommended)
docker-compose up -d
# Run with Docker CLI (persistent volumes)
docker run -d \
--name omni-cli \
-p 2222:22 \
-p 8000:8000 \
-v $(pwd)/omni-data:/data \
-v $(pwd)/omni-config:/config \
-e PUID=$(id -u) \
-e PGID=$(id -g) \
-e OPENAI_API_KEY=sk-... \
-e GEMINI_API_KEY=AIza... \
omni-cli
# Connect to running container
ssh omni@localhost -p 2222
# Password: changeme (or whatever was set during build)
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 · 739 lines · 5,037 tokens per session scan A 5efefac306f6
omni-cli AGENTS.md is an instructions file published in the GitHub repository mabelisle/omni-cli (6 stars, last pushed 7mo ago), licensed Apache-2.0. It adds 5,037 tokens to every session, about $0.0252 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
Project-AMBER AGENTS.md
Instructions for JJHbrams/Project-AMBER, covering agent orchestration, roles and non-negotiable rules.
all-agents-mcp CLAUDE.md
Instructions for Dokkabei97/all-agents-mcp, covering claude.md, project overview, build & development commands, architecture and entry flow.
obsidian-agent-client AGENTS.md
AGENTS.md instructions for RAIT-09/obsidian-agent-client, covering agent client plugin - llm developer guide, architecture, data flow, acp event flow (single path) and permission flow.
entwurf AGENTS.md
Instructions for junghan0611/entwurf, covering agents.md — maintainer guidelines for entwurf, north star — one forged screwdriver, architecture, hard rules and acp plugin boundary.
maestro-orchestrate GEMINI.md
Instructions for josstei/maestro-orchestrate, covering maestro techlead orchestrator, startup checks, gemini cli integration constraints, context budget and settings reference.
openharness AGENTS.md
Instructions for mifunedev/openharness, covering open harness — orchestrator, what open harness is, 1. agent work stays inside the sandbox, 2. coding-harness choice does not change the workspace and 3. remote and unattended operation are normal.