learn

learn is a skill for Claude Code, Codex from wardawgmalvicious/agent-config. It costs 163 tokens per session (2,128 once invoked), scanned A, original, MIT.

A session-learning guide that turns discoveries, mistakes, and missing instructions into proposed updates to an agent’s lasting skills and rules.

In plain words
What is it for?
Use it to record a documentation-versus-reality gap, add a missing troubleshooting step, or preserve the cause of a confusing error.
Why use it?
It prevents the same non-obvious problem from being rediscovered in later sessions. It also separates proposed edits from approved changes.

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/wardawgmalvicious/agent-config/learn
Any agent
npx skills add wardawgmalvicious/agent-config --skill learn
Clone the repo
git clone --depth 1 https://github.com/wardawgmalvicious/agent-config

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 learn

README.md
[![agentmods](https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/learn.svg)](https://agentmods.dev/skills/wardawgmalvicious/agent-config/learn)
Your own site
<a href="https://agentmods.dev/skills/wardawgmalvicious/agent-config/learn"><img src="https://agentmods.dev/badge/skills/wardawgmalvicious/agent-config/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 163 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,128 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 $0.00163 $0.02128
Opus 5 $0.00081 $0.01064
Sonnet 5 $0.00033 $0.00426
Haiku 4.5 $0.00016 $0.00213

Measured yesterday against content hash fb9da53b374c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

learn 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.

skills/workflow/learn/SKILL.md · 181 lines

How it starts

The opening of the file, as written. The whole thing — 181 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Learn: capture session learnings into skills and rules

Turn something discovered during this session into a durable, verified edit to the guidance that should have covered it. The goal is that the next session never has to rediscover it.

This skill proposes; it does not commit. Edits land only after the user approves the diff, and committing is handed to /commit.

The inverse skill is /author-skill: /learn folds a learning into guidance that already exists, /author-skill creates guidance that has no home yet. If the right destination for a learning turns out to be a skill this repo does not have, that is an /author-skill job.

This repo lives at C:\Repos\Personal\agent-config; ~/.claude/skills holds one junction per skill into it, so /learn may fire from a session in any repo. All repo-relative paths and commands below (grep, the lint script, /commit) run from that repo root, not the session's cwd.

Step 1 — Identify what was learned

Reflect on the session, not just the last message. Candidate learnings:

  • A skill or rule said X; reality was Y (doc-vs-reality gap).
  • A step was missing and cost debugging time.
  • An error message whose cause was non-obvious.
  • A constraint / limit / version change not documented anywhere here.
  • A user correction that reveals a general principle.

For each candidate, state in one or two sentences: problem → root cause → correct approach → generalization. Drop anything that is one-off, already obvious from the code, or only matters to this conversation. Confirm the list with the user before proceeding if it contains more than one item or you're unsure which matters.

Step 2 — Identify which guidance was in use (automatic)

Do not ask the user which skill was used. Reconstruct it:

  1. Skills invoked this session — every Skill tool call and every skill whose content appears in context (the <command-name> / loaded-skill blocks). Record the name: of each.
  2. Rules auto-loaded — any rules/coding-*.md content present in context, triggered by files in session scope (paths: globs).
  3. Global CLAUDE.md or rule sections relied on — e.g. the uv guidance (claude/CLAUDE.md) or the Fabric serialization rule (rules/fabric-git-serialization.md).
  4. Tools used — MCP servers / CLIs (fab, pbir, fabric-cicd, Fabric REST) point at the skill that owns them even if it wasn't explicitly invoked. Map by the skill's description.
  5. If nothing was loaded but a skill should have triggered, that is itself a learning: the fix is the skill's description (trigger phrases), not its body.

Read the full file on GitHub · 181 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 Changed · +3 lines fb9da53b374c
  2. 5d ago First seen · 178 lines · 163 tokens per session scan A 0ff1215fd3ed

Subscribe to this mod's changes

learn is a skill published in the GitHub repository wardawgmalvicious/agent-config (1 stars, last pushed today), licensed MIT. It adds 163 tokens to every session and 2,128 once invoked, about $0.0008 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 2026-08-31.

Related

Other skills, from other repositories

llm-app-patterns

Production-ready patterns for building LLM applications. Covers RAG pipelines, agent architectures, prompt IDEs, and LLMOps monitoring. Use when designing AI applications, implementing RAG, building agents, or setting up LLM observability.

davila7/claude-code-templates · 54 tokens

email-sequence

When the user wants to create or optimize an email sequence, drip campaign, automated email flow, or lifecycle email program. Also use when the user mentions "email sequence," "drip campaign," "nurture sequence," "onboarding emails," "welcome sequence," "re-engagement emails," "email automation," or "lifecycle…

davila7/claude-code-templates · 84 tokens

qa-test-planner

Generate comprehensive test plans, manual test cases, regression test suites, and bug reports for QA engineers. Includes Figma MCP integration for design validation.

davila7/claude-code-templates · 34 tokens

gepetto

Creates detailed, sectionized implementation plans through research, stakeholder interviews, and multi-LLM review. Use when planning features that need thorough pre-implementation analysis.

davila7/claude-code-templates · 35 tokens

guidance

Control LLM output with regex and grammars, guarantee valid JSON/XML/code generation, enforce structured formats, and build multi-step workflows with Guidance - Microsoft Research's constrained generation framework.

davila7/claude-code-templates · 38 tokens

gemini-api-agent-platform

Guides the usage of the Gemini API on Agent Platform with the Google Gen AI SDK for enterprise AI applications. Covers SDK usage (Python, JS/TS, Go, Java, C#), capabilities like Live API, tools, multimedia generation, caching, and batch prediction.

davila7/claude-code-templates · 61 tokens