jmcomic-ai AGENTS.md

jmcomic-ai AGENTS.md is an instructions file for Codex, OpenCode from hect0x7/jmcomic-ai. It costs 1,799 tokens per session, scanned A, original, MIT.

Repository guidance for agents developing JMComic AI, a project that turns a comic crawler into tools that AI agents can use.

In plain words
What is it for?
Researching the codebase and making agent-focused changes to services, MCP tools, documentation, and skill installation.
Why use it?
It explains the project structure, development principles, and where its core logic, agent interface, and skill management live.

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/hect0x7/jmcomic-ai/agents-md
Clone the repo
git clone --depth 1 https://github.com/hect0x7/jmcomic-ai

Made for: Codex, OpenCode.

Wrote 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.

agentmods badge for jmcomic-ai AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/hect0x7/jmcomic-ai/agents-md.svg)](https://agentmods.dev/instructions/hect0x7/jmcomic-ai/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/hect0x7/jmcomic-ai/agents-md"><img src="https://agentmods.dev/badge/instructions/hect0x7/jmcomic-ai/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,799 This file is loaded in full into every session.
When invoked 1,799 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 $0.01799 $0.01799
Opus 5 $0.00899 $0.00899
Sonnet 5 $0.00360 $0.00360
Haiku 4.5 $0.00180 $0.00180

Measured 5d ago against content hash d808bd098bd1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

jmcomic-ai 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 5d 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 · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AI Agent Development Guide for JMComic AI

This document provides instructions and best practices for AI Agents (like Antigravity) to develop, maintain, and extend the jmcomic-ai project.

🎯 Core Philosophy

The mission of this project is to transform the JMComic crawler into an AI-native cognitive asset.

  • Tools over Scripts: Don't just write scripts; build robust MCP tools that agents can use to reason and act.
  • Documentation as Code: Documentation (like SKILL.md) is the "brain" of the agent. It must be kept in sync with the implementation.
  • Self-Introspection: The project should expose its own schema and reference through MCP Resources.

🏗️ Architecture for Agents

  • src/jmcomic_ai/core.py: The "Brain". All business logic and tool implementations reside here in JmcomicService.
  • src/jmcomic_ai/mcp/server.py: The "Interface". Uses FastMCP to dynamically register methods from JmcomicService as MCP tools.
  • src/jmcomic_ai/skills/manager.py: The "Distributor". Owns platform-specific Agent Skills installation paths and safe install/uninstall behavior.
  • reference/jmcomic_src/: The "Knowledge Base". Contains the source code of the underlying jmcomic library. Always read this first when implementing new tools.

[!IMPORTANT] CRITICAL SOURCE CODE RULE Do NOT attempt to locate the jmcomic source code using python -c "import jmcomic; print(jmcomic.__file__)" or pip show. The installed version in site-packages is IRRELEVANT for development reference. You MUST strictly use the local copy in reference/jmcomic_src/ for all code analysis and logic extraction. Ignoring this rule leads to incorrect path assumptions and wasted steps.

When asked to add a new feature or tool, follow these steps:

1. Research & Discovery

  • STOP & READ: Go directly to reference/jmcomic_src/. Do not check installed packages.
  • Search reference/jmcomic_src/ to find the relevant logic in the base library.
  • For example, if adding a "favorite" feature, search for favorite in the reference code to see how JmcomicClient handles it.

Read the full file on GitHub · 123 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. 5d ago First seen · 123 lines · 1,799 tokens per session scan A d808bd098bd1

Subscribe to this mod's changes

jmcomic-ai AGENTS.md is an instructions file published in the GitHub repository hect0x7/jmcomic-ai (100 stars, last pushed 24d ago), licensed MIT. It adds 1,799 tokens to every session, about $0.0090 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.