agentmods.dev

todo-mindmap

todo-mindmap is a skill for Claude Code from grburgess/mindgap. It costs 150 tokens per session (1,502 once invoked), scanned A, original, MIT.

A skill that records ideas and to-dos in a connected knowledge graph, lets you review open items, and marks finished work as closed.

In plain words
What is it for?
Use it to capture ideas, review outstanding work, and close tasks when they are done.
Why use it?
It keeps reminders linked to their project and context instead of losing them in a simple list.

Skill for Claude Code

Written for Claude Code: SessionEnd hook event. Also seen: mentions AGENTS.md.

Part of the mindgap plugin — 13 skills shipped together

not rated 0repo changed 23d ago A scan 150 tokens original MIT

Good fit Use it to capture ideas, review outstanding work, and close tasks when they are done.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/grburgess/mindgap/todo-mindmap
View source ↗ grburgess/mindgap
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.

Any agent
npx skills add grburgess/mindgap --skill todo-mindmap
Clone the repo
git clone --depth 1 https://github.com/grburgess/mindgap

Made for: Claude Code.

Or install mindgap, the plugin that ships this one along with the rest of its 13 skills.

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 todo-mindmap

README.md
[![agentmods](https://agentmods.dev/badge/skills/grburgess/mindgap/todo-mindmap/github.svg)](https://agentmods.dev/skills/grburgess/mindgap/todo-mindmap)
Your own site
<a href="https://agentmods.dev/skills/grburgess/mindgap/todo-mindmap"><img src="https://agentmods.dev/badge/skills/grburgess/mindgap/todo-mindmap/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.

agentmods 80×15 button for todo-mindmap

Your own site · 80×15
<a href="https://agentmods.dev/skills/grburgess/mindgap/todo-mindmap"><img src="https://agentmods.dev/badge/skills/grburgess/mindgap/todo-mindmap.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 150 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00150 $0.01502
Opus 5.5 $0.00060 $0.00601
Sonnet 5.5 $0.00030 $0.00300
Haiku 4.5 $0.00015 $0.00150

Measured 23d ago against content hash ff8b8664cdb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

todo-mindmap 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 23d 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.

mindgap-plugin/skills/todo-mindmap/SKILL.md · 110 lines

How it starts

The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.

todo-mindmap

Ideas and todos live in the graph, not in a list. Each one hangs off the project it belongs to, so reviewing todos also surfaces the surrounding context, and closing one leaves a trail instead of a deletion. Graph writes obey AGENTS.md.

Dispatch

The user says Verb
"todo:", "idea:", "we should X", "remind me to X", "don't let me forget X" CAPTURE
"what's outstanding", "what are my todos", "what should I work on", "anything open on X" REVIEW
"that's done", "finished X", "drop that one" CLOSE

Inside a loop-system or meta-trainer session → stop, those own their memory protocol.

Node contract

Field Value
id todo-<slug>
type todo
title imperative one-liner
body what / why / what "done" means; [[wiki-links]] to related nodes
tags todo + exactly one status:open|doing|done|dropped + area tags + optional someday
confidence 1.0 — never overloaded as priority
created_by skill:todo-mindmap
urls optional — Jira ticket, PR, file path

Edges — ≥1 always, explicit in the payload, never an island:

rel target cardinality
part_of project / repo / loop node exactly one (primary anchor)
relates_to concepts, papers, decisions it touches 0..n
depends_on blocker — a node or another todo 0..n
resolved_by what closed it — jira-ticket, page, repo node 0..n, added at CLOSE

Wiki-links alone are not durable: sync_wiki_edges prunes derived mentions edges when the body changes. Anchors go in the payload edges.

CAPTURE

  1. mindgap_find on slug fragments + title words. A close match → upsert that id; never mint a near-duplicate.
  2. mindgap_find / mindgap_context to resolve the anchor project.
  3. One mindgap_ingest call: node + all edges (validated whole-payload, no partial commit).
  4. Reply with the id and the anchor.

No plausible anchor exists → create the project node in the same payload rather than orphan the todo. At most one clarifying question — capture that interrogates stops being used. A missing anchor is worth asking about; a missing done-criterion is not.

Read the full file on GitHub · 110 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. 23d ago Changed · -1 lines ff8b8664cdb4
  2. 2mo ago First seen · 111 lines · 150 tokens per session scan A 781e5cefa4fa

Subscribe to this mod's changes

todo-mindmap is a skill published in the GitHub repository grburgess/mindgap (0 stars, last pushed 23d ago), licensed MIT. It adds 150 tokens to every session and 1,502 once invoked, about $0.0006 per session on Opus 5.5. 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 2026-09-04.

Memory and contextProductivity
Related

todo-mindmap compared with skills from other repositories

todo-mindmap next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
todo-mindmapgrburgess/mindgapSkill023d agoMITA150Claude Code
Migratedanielmiessler/LifeOSSkill20kyesterdayMITA104Claude Code, Codex
Cortexdanielmiessler/LifeOSSkill20kyesterdayMITA184Claude Code
Profiledanielmiessler/LifeOSSkill20kyesterdayMITA108Claude Code, Codex
wiki-dashboardAr9av/obsidian-wikiSkill3.7kyesterdayMITA42Claude Code
relevance-coarse-filterelvisun/newsjackSkill1.7kyesterdayMITA57Claude Code
session-compactcodeaholicguy/ai-devkitSkill1.7k2d agoApache-2.0A39Claude Code