learn

A command for saving one insight, decision, rule, or task to the coding agent’s long-term project memory.

In plain words
What is it for?
Use it to record architecture choices, constraints, testing lessons, project tasks, and other durable knowledge under organized categories and tags.
Why use it?
It prevents important context from being lost between sessions and makes saved information easier to find later.

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/hautc-it/cil/learn
Clone the repo
git clone --depth 1 https://github.com/hautc-it/cil

Made for: Claude Code.

Per session 21 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 413 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 $0.00021 $0.00413
Opus 5 $0.00010 $0.00206
Sonnet 5 $0.00004 $0.00083
Haiku 4.5 $0.00002 $0.00041

Measured yesterday against content hash 80b82b89c6a1, 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.

.claude/commands/learn.md · 51 lines

What it actually says

/learn

Arguments: $ARGUMENTS

Persist a learning, decision, or constraint to memory.


Step 1 — Classify category

  • decision — architecture or design choice made
  • constraint — limit or rule that must be respected
  • learning — insight, lesson, or corrected assumption
  • task — work item for future sessions
  • architecture — structural or system design fact

Step 2 — Pick a topic tag from this taxonomy

Prepend exactly one of these as the first tag, so future memory_search can filter by topic:

  • navigation — file paths, finding code, project layout
  • editing — code change patterns, refactoring techniques
  • testing — test approach, framework quirks, coverage gaps
  • git — commits, branches, merge/rebase patterns
  • quality — lint, types, formatting, style rules
  • context — when to clarify vs assume, scope rules
  • architecture — design decisions, module boundaries
  • performance — optimization, profiling, bottlenecks
  • claude-code — sessions, modes, CLAUDE.md, skills, subagents, hooks, MCP
  • prompting — scope, constraints, acceptance criteria
  • debugging — root-cause findings, reproduction steps

Step 3 — Extract additional tags

From $ARGUMENTS, extract 1–4 more specific keywords (libraries, components, files).

Step 4 — Store

memory_store("[category]", "$ARGUMENTS", ["[topic-tag]", "tag2", "tag3"])

Step 5 — Confirm

Report: Stored [category] (topic: [topic-tag]): [brief summary]

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 · 51 lines · 21 tokens per session scan A 80b82b89c6a1

Subscribe to this mod's changes

learn is a command published in the GitHub repository hautc-it/cil (1 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session and 413 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.