insight-capture-format

insight-capture-format is a skill for Claude Code, Codex from Abilityai/cornelius. It costs 36 tokens per session (544 once invoked), scanned A, original, MIT.

A standard note format for capturing personal insights in a knowledge base. It records the insight, its type, source, distinctiveness, related ideas, and keywords.

In plain words
What is it for?
Use it when recording original theories, contrarian views, mental models, patterns, reading reflections, or other insights from your own thinking.
Why use it?
It gives different insight-capture sessions a consistent structure, making personal reasoning easier to preserve and find later. It also encourages links to supporting, contrasting, or follow-up ideas.

Skill for Claude CodeCodex

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 skills/abilityai/cornelius/insight-capture-format
Any agent
npx skills add Abilityai/cornelius --skill insight-capture-format
Clone the repo
git clone --depth 1 https://github.com/Abilityai/cornelius

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.

agentmods badge for insight-capture-format

README.md
[![agentmods](https://agentmods.dev/badge/skills/abilityai/cornelius/insight-capture-format.svg)](https://agentmods.dev/skills/abilityai/cornelius/insight-capture-format)
Your own site
<a href="https://agentmods.dev/skills/abilityai/cornelius/insight-capture-format"><img src="https://agentmods.dev/badge/skills/abilityai/cornelius/insight-capture-format.svg" alt="Measured on agentmods" height="20"></a>
Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 544 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00036 $0.00544
Opus 5 $0.00018 $0.00272
Sonnet 5 $0.00007 $0.00109
Haiku 4.5 $0.00004 $0.00054

Measured 5d ago against content hash d80691ed0b7b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

insight-capture-format 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.

.claude/skills/insight-capture-format/SKILL.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Insight Capture Format

When capturing an insight, use this format:

> **[CAPTURING INSIGHT]**
>
> **Title:** `[[Concise title that captures the unique perspective]]`
> **Type:** (Personal Theory / Contrarian View / Synthesis / Experience Wisdom / Mental Model / Pattern / Value Discovery / Reading Reflection)
> **Uniqueness:** What makes this insight distinctively yours
> **Source:** [If from reading: Book/Article title, Author, Page/Location]
>
> ---
>
> [Body: The insight in 1-3 sentences, preserving your authentic voice and reasoning]
>
> ---
> **Connections:**
> * `[[Related Insight]]` - how this builds on previous thinking
> * `[[Contrasts With]]` - ideas this challenges or refines
> * `[[Examples]]` - concrete instances that demonstrate this
> * `[[Questions Raised]]` - what this makes you wonder about
>
> **Keywords:** #insight-type #topic #source-if-applicable

Insight Types to Harvest

Actively hunt for and categorize these types of unique insights:

Type Description Example Signal
Personal Theory Original explanatory models "I think X works because Y"
Contrarian View Challenges conventional wisdom "Everyone says X, but I've found Y"
Synthesis Insight Novel connections between concepts "A is like B in this unexpected way"
Experience Wisdom Hard-won lessons "After failing at X multiple times, I realized Y"
Mental Model Unique cognitive frameworks "I always approach X by thinking of it as Y"
Pattern Recognition Personal observations "I've noticed that whenever X happens, Y follows"
Value Discovery Evolution of priorities "I used to think X mattered, but now Y is what counts"
Reading Reflection Thoughts from books/articles With proper source attribution

Knowledge Base Integrity Principles

The knowledge base must be:

  • Non-redundant: No duplicate insights - always search before creating
  • Self-consistent: Notes should not contradict each other without explicit acknowledgment
  • Non-contradicting: When conflicts arise, resolve or document the tension explicitly

Read the full file on GitHub · 58 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 · 58 lines · 36 tokens per session scan A d80691ed0b7b

Subscribe to this mod's changes

insight-capture-format is a skill published in the GitHub repository Abilityai/cornelius (106 stars, last pushed 12d ago), licensed MIT. It adds 36 tokens to every session and 544 once invoked, about $0.0002 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

media-ingest

Ingest video, audio, PDF, book, screenshot, and GitHub repo content into the brain. Multi-format handling with entity extraction and backlink propagation. Covers video-ingest, youtube-ingest, and book-ingest subtypes.

garrytan/gbrain · 52 tokens

mem0-oss-to-platform

Plan and then execute a migration of a project from the mem0 open-source / self-hosted SDK (the local Memory class) to the mem0 Platform / hosted / managed SDK (the MemoryClient class). Use this whenever a developer wants to move, switch, or migrate their mem0 usage off OSS/self-hosted to the hosted API — e.g.…

mem0ai/mem0 · 273 tokens

Cortex

Operate Cortex, the LifeOS memory system — the typed Knowledge Archive (People, Companies, Ideas, Research with typed related: links) plus recall of prior work sessions, ISAs, and conversations. Search, add, harvest, develop, ingest, distill, graph-navigate, recall. USE WHEN cortex, knowledge, knowledge base, search…

danielmiessler/LifeOS · 196 tokens

agent-memory

../../../engineering/agent-memory/skills/agent-memory/SKILL.md.

alirezarezvani/claude-skills · 0 tokens

memory

Use when the user asks to remember, recall, forget, update, search, or inspect durable OpenSquilla memory, including profile facts in USER.md and long-term notes in MEMORY.md or memory//.md.

opensquilla/opensquilla · 44 tokens

ha-data-stores

Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…

shiwenwen/hope-agent · 115 tokens