A guide for reading and changing an M3E mind map through a local web API. A mind map is a tree of connected ideas or project items, and the guide covers finding maps, editing nodes, and checking saved results.

Use it to view, search, add, update, move, color, delete, or reorganize map nodes and to save and verify those changes through the API.

It gives map changes a defined read, modify, write, and verify process, reducing the chance of editing the wrong map or breaking its structure. It also explains the local address and map identifiers needed for requests.

How akaghef/M3E configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to akaghef/M3E. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/akaghef/M3E/main/.agents/skills/m3e-map/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/akaghef/M3E

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/akaghef/m3e/m3e-map/github.svg)](https://agentmods.dev/skills/akaghef/m3e/m3e-map)

Your own site

<a href="https://agentmods.dev/skills/akaghef/m3e/m3e-map"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/m3e-map/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/akaghef/m3e/m3e-map"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/m3e-map.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 127 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 3,083 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00127	$0.03083
Opus 5.5	$0.00051	$0.01233
Sonnet 5.5	$0.00025	$0.00617
Haiku 4.5	$0.00013	$0.00308

Measured 5d ago against content hash d28ab519f4b3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

m3e-map 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 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

For complex modifications (>3 nodes), write a one-shot Node.js script to `%TEMP%` (Windows) / `/tmp` and execute. **Bash `/tmp` ≠ Node.js `/tmp` on Windows** — use absolute Windows path like `c:/Users/Akaghef/AppData/Loc

.agents/skills/m3e-map/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

M3E Map API Skill

Operate on the M3E mind-map through its local REST API.

API Basics

Base URL: http://localhost:4173 (beta — default for dev / agent operations; override with M3E_PORT env var. final は 38482)
Content-Type: application/json; charset=utf-8
Auth: None (local only)
Map ID: Each map has its own opaque ID like map_BG9BZP6NRDTEH1JYNDFGS6S3T5. There is no default doc ID — discover the target map via GET /api/maps (filter by label).

Workflow

For any map operation, follow this sequence:

Identify the map — if not given, list GET /api/maps and pick by label (e.g. "開発" = DEV, "研究" = RESEARCH)
Read the display contract first — for writes, determine the target facet and display goals before touching structure (see references/facet-contracts.md and references/display-intent.md)
Read the current state (see references/read.md)
Modify in-memory while maintaining invariants and the chosen display contract (see references/data-model.md)
Write the full state back via POST or PUT (see references/write.md)
Verify the response — success returns { "ok": true, "savedAt": "...", "mapId": "..." }

Route structural decisions to Map Manager

This skill executes map reads and writes. It does not own scope granularity, scopen / unscopen policy, layouting / display intent, alias vs move vs GraphLink choices across facets, or worker handoff boundaries.

For those decisions, consult docs/protocols/map-manager/README.md, docs/protocols/map-manager/gates.md, and the map-manager skill before mutation.

For complex modifications (>3 nodes), write a one-shot Node.js script to %TEMP% (Windows) / /tmp and execute. Bash /tmp ≠ Node.js /tmp on Windows — use absolute Windows path like c:/Users/Akaghef/AppData/Local/Temp/script.js when invoking node. For 1-3 node changes, inline JSON with curl is fine.

Read the full file on GitHub · 231 lines

Files

What ships with it

4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

5d ago First seen · 231 lines · 127 tokens per session scan A d28ab519f4b3

Subscribe to this mod's changes

m3e-map is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 127 tokens to every session and 3,083 once invoked, about $0.0005 per session on Opus 5.5. 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 2026-10-02.

Project management

story-readiness

Is a story implementation-ready? Checks clear acceptance criteria, open questions, ADR refs. READY/NEEDS WORK/BLOCKED/NOT ASSESSED.

Donchitos/Claude-Code-Game-Studios · 35 tokens

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

M3E: Skill for Claude Code