learn-lessons

A retrospective review of completed coding work that extracts repeatable patterns, design decisions, and practices from it. The results are written into reusable skills and AGENTS.md instructions.

In plain words
What is it for?
Capturing naming and file-structure conventions, TypeScript patterns, testing approaches, architectural choices, and solutions to difficult technical problems.
Why use it?
It prevents useful lessons from being lost after a feature, fix, branch, or pull request is finished.

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/jimmypaolini/codebase/learn-lessons
Any agent
npx skills add JimmyPaolini/codebase --skill learn-lessons
Clone the repo
git clone --depth 1 https://github.com/JimmyPaolini/codebase

Made for: Claude Code, Codex.

Per session 139 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,382 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 $0.00139 $0.03382
Opus 5 $0.00069 $0.01691
Sonnet 5 $0.00028 $0.00676
Haiku 4.5 $0.00014 $0.00338

Measured yesterday against content hash f2f5f87e7c9f, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn-lessons 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.

.agents/skills/learn-lessons/SKILL.md · 304 lines

How it starts

The opening of the file, as written. The whole thing — 304 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn Lessons

You are a senior software engineer and technical knowledge curator. Your role is to deeply analyze completed work — code changes, a branch diff, or a PR — and extract the coding patterns, architectural decisions, and best practices embedded in that work. You then write those patterns into skills and AGENTS.md so future agents apply the same approach automatically without being re-taught.

The primary focus is how code was written: naming conventions, module structure, TypeScript idioms, error handling patterns, testing approaches, and architectural choices. Agent workflow behaviors (which tools to call, how to sequence file edits) are secondary — capture those only when they reveal a repeatable coding pattern.

Your output is not a report. It is concrete updates to skills and AGENTS.md that encode the patterns found.

When to Use This Skill

Primary use cases — coding patterns

  • After implementing a new module, feature, or architectural pattern worth repeating
  • When the code introduces a naming convention, file structure, or TypeScript idiom not yet in any skill
  • After solving a non-obvious technical problem (error handling, async pattern, type narrowing) the right way
  • When a PR review revealed a gap between what was written and the project's preferred style
  • When asked to "remember how we did this", "document this pattern", or "make sure future agents do it this way"

Secondary use cases — agent workflow

  • After a session with significant back-and-forth or corrections
  • After merging or closing a PR, to capture workflow lessons
  • When asked to "retrospect", "capture lessons", or "improve agent skills from this work"
  • Proactively at the end of a large implementation task before submitting changes

Scope of Analysis

The skill examines one or more of these inputs — use whichever are available:

Input How to Access
Session log Read the Copilot session debug log at {{VSCODE_TARGET_SESSION_LOG}} (current session)
Local changes Run git diff HEAD or git diff main to see uncommitted/unmerged changes
Branch diff Run git log main..HEAD --oneline then git diff main...HEAD
Pull request Use gh pr view <number> --json title,body,files and gh pr diff <number>
Conversation history Review the current conversation for retries, corrections, and course changes

Read the full file on GitHub · 304 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. yesterday First seen · 304 lines · 139 tokens per session scan A f2f5f87e7c9f

Subscribe to this mod's changes

learn-lessons is a skill published in the GitHub repository JimmyPaolini/codebase (0 stars, last pushed yesterday), licensed MIT. It adds 139 tokens to every session and 3,382 once invoked, about $0.0007 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 2026-09-01.

Related

Other skills, from other repositories

book-mirror

Take any book (EPUB/PDF), produce a personalized chapter-by-chapter analysis. Each chapter is preserved in detail (The Chapter) and mirrored back to the reader's actual life (The Mirror) using brain context. The mirror observes and resonates — a friend pointing out parallels, NOT a consultant rearranging the reader's…

garrytan/gbrain · 138 tokens

ljg-learn

Deep concept anatomist that deconstructs any concept through 8 exploration dimensions (history, dialectics, phenomenology, linguistics, formalization, existentialism, aesthetics, meta-philosophy) and compresses insights into an epiphany. Use when user asks to explain, dissect, or deeply understand a concept, term, or…

lijigang/ljg-skills · 113 tokens

eli5

Explain research, papers, or technical ideas in plain English with minimal jargon, concrete analogies, and clear takeaways. Use when the user says "ELI5 this", asks for a simple explanation of a paper or research result, wants jargon removed, or asks what something technically dense actually means.

companion-inc/feynman · 63 tokens

deck-course-module

暖纸背景 + Playfair, 左侧学习目标常驻, 含 MCQ 自测页.

nexu-io/html-anything · 25 tokens

pedagogy-review

Holistic pedagogical review of a lecture deck (.qmd or .tex). Checks narrative arc, prerequisite assumptions, worked examples, notation clarity, and deck-level pacing. Use when user says "pedagogy review", "does this teach well?", "is the flow right?", "will students follow?", "review the narrative", or before…

pedrohcgs/claude-code-my-workflow · 90 tokens

master-yinguang

Use when user asks about 印光大师, 净土, 念佛, 持名念佛, 十念法, 摄耳谛听, 老实念佛, 信愿行, 带业往生, 仗佛慈力, 自力他力, 竖出横超, 往生, 极乐, 阿弥陀佛, 净土三经, 敦伦尽分, 闲邪存诚, 因果报应, 文钞, 一函遍复, or wants teaching in 印光大师 Yinguang's voice. Triggers include "印光"、"文钞"、"老实念佛"、"信愿行"、"带业往生"、"仗佛慈力"、"横超竖出"、"都摄六根"、"净念相继"、"敦伦尽分"、"闲邪存诚"、"因果"、"十念法"、"摄耳谛听"、"一函遍复"、"净土三经"、"往生" — invoke…

xr843/Master-skill · 274 tokens