manage-thinking-topics

manage-thinking-topics is a skill for Claude Code from Abilityai/cornelius. It costs 29 tokens per session (3,781 once invoked), scanned A, original, MIT.

A topic-management workflow for an incubation loop: a system that develops open questions over time until they become documented conclusions or are dropped.

In plain words
What is it for?
Use it to add questions, review topic status, turn settled findings into permanent notes or reports, and retire stale topics.
Why use it?
It keeps questions, reasoning journals, conclusions, and retired topics organized instead of leaving analysis scattered or unfinished.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths; mentions CLAUDE.md.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python3 resources/local-brain-search/search.py "[central question keywords]" --limit 5 --mode spreading 2>/dev/null.

Good fit Use it to add questions, review topic status, turn settled findings into permanent notes or reports, and retire stale topics.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius
agentmods
npx agentmods add skills/abilityai/cornelius/manage-thinking-topics

Made for: Claude Code.

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 manage-thinking-topics

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/cornelius/manage-thinking-topics.svg)](https://agentmods.dev/skills/abilityai/cornelius/manage-thinking-topics)
Your own site
<a href="https://agentmods.dev/skills/abilityai/cornelius/manage-thinking-topics"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/manage-thinking-topics.svg" alt="Measured on agentmods" height="20"></a>
Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,781 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 3 findings, up to high

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • high Rogue Agent · line 424
    Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.
    Fix: Prevent the skill from modifying its own code, SKILL.md, or configuration files. Treat skill files as read-only at runtime.
  • medium Agent Snooping · line 14
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 427
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
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 $0.00029 $0.03781
Opus 5 $0.00015 $0.01891
Sonnet 5 $0.00006 $0.00756
Haiku 4.5 $0.00003 $0.00378

Measured 8d ago against content hash 60e64db1ca0b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

manage-thinking-topics 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 8d 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.

.claude/skills/manage-thinking-topics/SKILL.md · 429 lines

How it starts

The opening of the file, as written. The whole thing — 429 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Manage Thinking Topics

Human-in-the-loop manager for the incubation loop topic registry. Handles the full lifecycle: seeding new questions into analysis, reviewing current status, graduating converged conclusions to permanent notes, and retiring topics no longer worth pursuing.

Companion skill: .claude/skills/incubation-loop/SKILL.md — the analytical engine that processes active topics.

State Dependencies

Source Location Read Write Description
Thinking Registry Brain/05-Meta/Thinking/THINKING-REGISTRY.md Master list of all topics + status
Topic Files Brain/05-Meta/Thinking/[topic-slug].md Per-topic reasoning journal
Permanent Notes Brain/02-Permanent/ Atomic crystallized conclusions (graph-integrated, future-reasoning substrate)
Synthesis Reports Brain/05-Meta/Reports/ Terminal crystallized conclusions (decision-input snapshots, excluded from LBS index)
AI Extracted Notes Brain/AI Extracted Notes/ Alternative destination for crystallized notes

Modes

Invoke with one of four modes. If no mode is provided, default to review.


Mode: review

Purpose: Show the full topic landscape at a glance - what's active, what needs crystallization, what's done.

Step 1: Read Registry

date '+%Y-%m-%d'

Read Brain/05-Meta/Thinking/THINKING-REGISTRY.md.

Step 2: For Each Active Topic - Load Summary

For each topic with status: active, read its thinking file. Extract:

  • run_count - how many iterations completed
  • last_run - date of last iteration
  • Current leading hypothesis + confidence score
  • Next move in rotation (run_count mod 6)
  • Any open questions flagged

Step 3: For Each Converged Topic - Load Summary

For each topic with status: converged, read its thinking file. Extract:

  • The converged conclusion (Current Best Answer from last run)
  • Confidence score at convergence
  • Run count at convergence

Read the full file on GitHub · 429 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. 8d ago First seen · 429 lines · 29 tokens per session scan A 60e64db1ca0b

Subscribe to this mod's changes

manage-thinking-topics is a skill published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 15d ago), licensed MIT. It adds 29 tokens to every session and 3,781 once invoked, about $0.0001 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens