learn

A command for reviewing the current coding session and recording durable, repository-specific lessons. It stores notes about recurring failures, toolchain quirks, dependency behavior, constraints, fixes, and verification commands.

In plain words
What is it for?
Use it after a surprising failure or useful fix to save a concise incident note, then search or list the notes to confirm it was recorded.
Why use it?
It prevents future agents from having to rediscover important project-specific problems and solutions.

Command for Claude Code

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/attunehq/nudge/learn
Clone the repo
git clone --depth 1 https://github.com/attunehq/nudge

Made for: Claude Code.

Per session 10 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 220 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 $0.00010 $0.00220
Opus 5 $0.00005 $0.00110
Sonnet 5 $0.00002 $0.00044
Haiku 4.5 $0.00001 $0.00022

Measured 2d ago against content hash 20f5a13a59bc, 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 2d 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/commands/nudge/learn.md · 29 lines

What it actually says

Review the current session history and decide whether anything should become a repo-local Nudge learned incident note.

Focus on hard-won, repo-specific knowledge that future agents should not have to rediscover: surprising failures, toolchain quirks, dependency behavior, environment constraints, fix patterns, and verification commands. Do not record generic programming advice, secrets, credentials, or one-off observations that are unlikely to recur.

If the user supplied arguments in $ARGUMENTS, use them as the focus area.

For each useful learning, record a note with nudge learn add. The note should include:

  • # <short specific title>
  • ## What went wrong
  • ## Fix
  • ## Verification

Prefer one concise note per incident. After writing notes, run nudge learn search <relevant query> or nudge learn list to confirm they were recorded.

If there is no durable repo-specific learning, say that clearly and do not create a 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.

  1. 2d ago First seen · 29 lines · 10 tokens per session scan A 20f5a13a59bc

Subscribe to this mod's changes

learn is a command published in the GitHub repository attunehq/nudge (82 stars, last pushed 17d ago), licensed Apache-2.0. It adds 10 tokens to every session and 220 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 2026-08-30.