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.
git clone --depth 1 https://github.com/Abilityai/corneliusnpx agentmods add skills/abilityai/cornelius/manage-thinking-topicsWrote 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.
[](https://agentmods.dev/skills/abilityai/cornelius/manage-thinking-topics)<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>- NVIDIA SkillSpector warn
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.
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 | $0.00029 | $0.03781 |
| Opus 5 | $0.00015 | $0.01891 |
| Sonnet 5 | $0.00006 | $0.00756 |
| Haiku 4.5 | $0.00003 | $0.00378 |
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.
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 completedlast_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
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.
- 8d ago First seen · 429 lines · 29 tokens per session scan A 60e64db1ca0b
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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…
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…
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…
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…