learn

A knowledge-capture command that turns a mistake, correction, or useful project pattern into a written rule for future work.

In plain words
What is it for?
Use it to add a concise, actionable lesson to a project’s CLAUDE.md file after confirming the wording.
Why use it?
It helps prevent the same mistake from happening again by recording the lesson in the project’s guidance file.

Command

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 commands/gpolanco/dev-workflows/learn
Clone the repo
git clone --depth 1 https://github.com/gpolanco/dev-workflows
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 258 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 $0.00013 $0.00258
Opus 5 $0.00006 $0.00129
Sonnet 5 $0.00003 $0.00052
Haiku 4.5 $0.00001 $0.00026

Measured yesterday against content hash 4d89281ab839, 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.

content/commands/learn.md · 33 lines

What it actually says

You are a knowledge capture assistant. Your job is to turn a lesson learned (a mistake, a correction, or a best practice) into a permanent project rule.

Follow this process:

  1. Ask the user what they learned. This could be:

    • A bug they found and how to avoid it
    • A pattern that works well in this codebase
    • A convention the AI should always follow
    • A mistake the AI made that should not be repeated
  2. Formulate a clear, actionable rule from the lesson. The rule should:

    • Be specific to this project
    • Be written as an imperative instruction
    • Include context about why it matters
    • Be concise (1-3 sentences)
  3. Append the rule to the project's CLAUDE.md file (or equivalent) under a ## Lessons Learned section. If the section does not exist, create it.

Format:

## Lessons Learned

- <Rule description>. Context: <why this matters>.

Confirm with the user before writing.

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 · 33 lines · 13 tokens per session scan A 4d89281ab839

Subscribe to this mod's changes

learn is a command published in the GitHub repository gpolanco/dev-workflows (1 stars, last pushed 2mo ago), licensed MIT. It adds 13 tokens to every session and 258 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 2026-08-31.