What is learning-capture?

A workflow for recording what was learned when a Work Item is finished. A Work Item is a tracked piece of engineering work, and the record separates what was implemented, changed, learned, and left unresolved.

Use it after implementation and verification to write a learning note covering results, decisions, surprises, knowledge updates, and pending work.

It prevents incomplete or failed work from being presented as finished and preserves decisions and knowledge that should be updated elsewhere.

learning-capture — Skill for Claude Code and Codex by Kaddo-kdd/kaddo

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 Kaddo-kdd/kaddo --skill learning-capture

Clone the repo

git clone --depth 1 https://github.com/Kaddo-kdd/kaddo

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/kaddo-kdd/kaddo/learning-capture/github.svg)](https://agentmods.dev/skills/kaddo-kdd/kaddo/learning-capture)

Your own site

<a href="https://agentmods.dev/skills/kaddo-kdd/kaddo/learning-capture"><img src="https://agentmods.dev/badge/skills/kaddo-kdd/kaddo/learning-capture/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/kaddo-kdd/kaddo/learning-capture"><img src="https://agentmods.dev/badge/skills/kaddo-kdd/kaddo/learning-capture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 244 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.

Model	Per session	Once invoked
Fable 5.1	$0.00032	$0.00244
Opus 5.5	$0.00013	$0.00098
Sonnet 5	$0.00006	$0.00049
Haiku 4.5	$0.00003	$0.00024

Measured yesterday against content hash af68feefaef1, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-26, from the pricing page.

Security

Grade A, and why

learning-capture 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 yesterday.

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.

kaddo-power/skills/learning-capture/SKILL.md · 42 lines

What it actually says

Learning Capture Skill

Purpose

Standardize how a Work Item's learning is captured when it closes.

When to use

When finishing a Work Item, after implementation and verification.

Inputs

The Work Item, the diff/result, and any decisions or surprises that came up.

Output

A learning record: what was implemented, what changed, what was learned, what decision emerged, which knowledge must be updated, and what remains pending.

Rules

Do not close a Work Item without validation.
Do not hide failures; record them honestly.
Do not assume everything is done if errors remain.

Quality checklist

Implemented vs changed vs learned are distinct.
Knowledge to update is named (ADR / capabilities / current-state).
Pending items are listed.

Example output

A short learning section appended to the Work Item or a learning note.

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.

yesterday First seen · 42 lines · 32 tokens per session scan A af68feefaef1

Subscribe to this mod's changes

learning-capture is a skill published in the GitHub repository Kaddo-kdd/kaddo (54 stars, last pushed today), licensed MIT. It adds 32 tokens to every session and 244 once invoked, about $0.0001 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 2026-09-25.

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

learning-capture