logan AGENTS.md

Project instructions for connecting AI agents to Logan, a tool for analyzing logs and chatting with users. They describe its local HTTP API, MCP server, real-time event stream, and agent-specific setup files.

In plain words
What is it for?
Configuring Claude Code, Cursor, Windsurf, Copilot, Codex, custom agents, or Python scripts to analyze logs and exchange messages with Logan.
Why use it?
They show different kinds of agents how to connect to Logan and which project files or communication method to use.

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/solidkeyab/logan/agents-md
Clone the repo
git clone --depth 1 https://github.com/SolidKeyAB/logan

Made for: Codex, OpenCode.

Per session 1,082 This file is loaded in full into every session.
When invoked 1,082 The same file — it is already loaded in full.
Security scan A 0 findings. 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 $0.01082 $0.01082
Opus 5 $0.00541 $0.00541
Sonnet 5 $0.00216 $0.00216
Haiku 4.5 $0.00108 $0.00108

Measured 2d ago against content hash 3a91c7ca7ccc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

logan 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 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.

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.

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.

LOGAN Agent Integration

LOGAN supports AI agent integration through its local HTTP API and MCP server. Any agent can connect to analyze logs and chat with the user.

Quick Start

Your Agent Supports What to Use Setup
MCP (Claude Code, Cursor, Windsurf) MCP tools .mcp.json already configured — tools auto-discovered
HTTP calls (Copilot, Codex, custom) REST API polling Read endpoints below, poll every 2-3s
Persistent connections (scripts) SSE stream Connect to /api/events for real-time

Agent-Specific Files

File Agent Description
.mcp.json MCP-compatible agents MCP server config (auto-discovered)
CLAUDE.md Claude Code Project instructions + MCP tool reference
.cursorrules Cursor Agent instructions + MCP/HTTP reference
.github/copilot-instructions.md GitHub Copilot HTTP polling instructions + endpoints
docs/AGENT_CHAT_GUIDE.md All agents Full integration guide with code examples
scripts/agent-chat-poll.py Any Python agent Ready-to-run polling chat script
scripts/agent-chat-sse.py Any Python agent Ready-to-run SSE chat script

API Reference (http://127.0.0.1:19532)

Chat

Method Endpoint Description
POST /api/agent-register Register as connected: {"name": "MyAgent"} (shows green dot)
POST /api/agent-message Send message: {"message": "text", "name": "MyAgent"}
GET /api/messages?since=TS Get messages after timestamp (ms)
GET /api/events?name=Name SSE stream (real-time, 1 agent max)
GET /api/agent-status Check if an agent is connected

Log Analysis

Method Endpoint Description
GET /api/status File info, line count, filter state
POST /api/open-file Open file: {"filePath": "..."}
GET /api/lines?start=N&count=M Read lines
POST /api/search Search: {"pattern": "...", "maxResults": 50}
POST /api/analyze Full analysis (levels, crashes, components)
POST /api/navigate Jump to line: {"line": 123}
POST /api/filter Filter: {"pattern": "ERROR"}
POST /api/clear-filter Remove filter

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 · 1,082 tokens per session scan A 3a91c7ca7ccc

Subscribe to this mod's changes

logan AGENTS.md is an instructions file published in the GitHub repository SolidKeyAB/logan (4 stars, last pushed 4d ago), licensed MIT. It adds 1,082 tokens to every session, about $0.0054 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 2026-08-31.