helix-pilot AGENTS.md

A project instruction file for helix-pilot, an AI tool setup that shares saved information between several AI tools. It documents the shared memory service, connection settings, and search interface.

In plain words
What is it for?
It is for configuring shared memory, checking the required service addresses and collection name, and using the optional HTTP search, add, and list operations.
Why use it?
It prevents the different tools from using mismatched memory locations, models, or connection settings.

Instructions file for CodexOpenCode

Install

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.

agentmods
npx agentmods add instructions/tsunamayo7/helix-pilot/agents-md
Clone the repo
git clone --depth 1 https://github.com/tsunamayo7/helix-pilot

Made for: Codex, OpenCode.

Per session 700 This file is loaded in full into every session.
When invoked 700 The same file — it is already loaded in full.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00700 $0.00700
Opus 5 $0.00350 $0.00350
Sonnet 5 $0.00140 $0.00140
Haiku 4.5 $0.00070 $0.00070

Measured 2d ago against content hash 941d62d46dd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

helix-pilot 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.

### HTTP API (for Codex CLI, curl, scripts)
AGENTS.md · 93 lines

How it starts

The opening of the file, as written. The whole thing — 93 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md — helix-pilot

Shared Memory (Mem0)

All AI tools (Claude Code, Codex CLI, Open WebUI, Ollama) share the same Mem0 memory.

Connection Spec (MUST match across all tools)

Key Value
Qdrant collection mem0_shared
Qdrant URL http://localhost:6333
Embedding model bge-m3 (dim=1024, via Ollama)
LLM for extraction ministral-3:8b (via Ollama)
Ollama URL http://localhost:11434
user_id tsunamayo7
HTTP API (optional) http://localhost:8080

IMPORTANT: Every tool MUST use Qdrant collection mem0_shared. Do NOT use the default collection name mem0_mcp_selfhosted. When adding a new AI tool, set MEM0_COLLECTION=mem0_shared explicitly.

HTTP API (for Codex CLI, curl, scripts)

# Search
curl -s -X POST http://localhost:8080/search \
  -H "Content-Type: application/json" \
  -d '{"query": "search term"}'

# Add
curl -s -X POST http://localhost:8080/add \
  -H "Content-Type: application/json" \
  -d '{"text": "content to save"}'

# List all
curl -s http://localhost:8080/list

MCP (for Claude Code)

Claude Code uses mem0_mcp_bridge.py via stdio, proxying to localhost:8080. Tools: search_memories, add_memory, get_memories.

Browser Use CLI 2.0

Web ブラウザ自動操作ツール。全 AI ツールから利用可能。

Global Install

C:\Users\tomot\.local\bin\browser-use.exe

MCP (for Claude Code)

browser-use --mcp (stdio) で .claude.json に登録済み。

CLI (for Codex CLI, scripts)

browser-use open https://example.com
browser-use state          # ページ状態取得
browser-use click 5        # 要素クリック
browser-use input 3 "text" # テキスト入力
browser-use screenshot out.png
browser-use extract "Get all product names"

Python (for Ollama)

from browser_use import Agent
from browser_use import ChatOllama

llm = ChatOllama(model="gemma3:27b")
agent = Agent("search for helix-pilot on GitHub", llm=llm)
agent.run_sync()

Rules

  • Search for related memories at session start
  • Save important decisions when user says "remember" or "save this"
  • Do not save routine Q&A

Read the full file on GitHub · 93 lines

Changes

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.

  1. 2d ago First seen · 93 lines · 700 tokens per session scan A 941d62d46dd1

Subscribe to this mod's changes

helix-pilot AGENTS.md is an instructions file published in the GitHub repository tsunamayo7/helix-pilot (4 stars, last pushed 4mo ago), licensed MIT. It adds 700 tokens to every session, about $0.0035 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.

Related

Other instructions, from other repositories