learn

learn is a command for coding agents from bondarewicz/dreamteam. It costs 41 tokens per session (1,245 once invoked), scanned A, original, MIT.

An end-of-session command that reviews what happened during a coding session and updates shared project memory. It can also record approved working rules for future sessions.

In plain words
What is it for?
Use it after a session to analyze signals, approve suggested lessons, save instructions, and refresh MEMORY.md.
Why use it?
It reduces the need to repeat project context and decisions every time work resumes. It keeps the learning process in one shared place for the team.

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/bondarewicz/dreamteam/learn
Clone the repo
git clone --depth 1 https://github.com/bondarewicz/dreamteam

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/commands/bondarewicz/dreamteam/learn.svg)](https://agentmods.dev/commands/bondarewicz/dreamteam/learn)
Your own site
<a href="https://agentmods.dev/commands/bondarewicz/dreamteam/learn"><img src="https://agentmods.dev/badge/commands/bondarewicz/dreamteam/learn.svg" alt="Measured on agentmods" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,245 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 $0.00041 $0.01245
Opus 5 $0.00020 $0.00622
Sonnet 5 $0.00008 $0.00249
Haiku 4.5 $0.00004 $0.00125

Measured 4d ago against content hash b234ae06959e, 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 4d 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.

commands/learn.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are the Dream Team Learning Loop for this session. Your job is to run the end-of-session learning step — the same step the team.md SESSION LEARNING (DB LOOP) section runs at the end of a /team session — adapted for ordinary (non-/team) Claude Code sessions.

The CLI is the single behavioral gate. All scrub, confidence, AC-8 self-check, consent rules, and projection determinism live in dreamteam learn (runLearn in bin/dreamteam.ts). Do not re-author any of that logic here.

Pre-cutover safe: dreamteam learn writes to the Dream Team workspace (~/.dreamteam/workspace/memory/<project>/) by default — it does NOT touch ~/.claude. The isUnderClaudeDir guardrail refuses ~/.claude without --installer-phase, which is only set by the slice-9 cutover script. Running /learn today is safe and reversible.


STEP 1 — Run the analyzer + approve auto-inferred pending

Invoke dreamteam learn in the current project directory:

dreamteam learn --project "$(basename "$(pwd)")"

If dreamteam is not on PATH (repo-source install, pre-npm):

bun "$(git rev-parse --show-toplevel)/bin/dreamteam.ts" learn --project "$(basename "$(pwd)")"

The CLI runs the full automated pipeline:

  1. ensure — idempotent DDL; no-op if tables already exist
  2. analyze — session analyzer reads recent eval findings; materializes candidate instincts
  3. approve auto-inferred pending — prompts Approve instinct #id [domain]: "trigger" (conf X.XX)? [y/N] per auto-inferred pending row. Answer y or n — no free text required. Human-directive rows are NOT presented here (they require the authorship act, Step 2).
  4. regenerate — always runs, even if steps 2–3 produced nothing. Writes MEMORY.md + topic files to the workspace projection dir.

The CLI prints a summary on completion. Done — full value delivered for the automated pipeline.


STEP 2 — Surface directive candidates in-conversation (FREE TEXT)

After the CLI completes, you have what it does not: the live session transcript. Identify up to 2–3 directive candidates — non-obvious behavioral preferences this session established:

Read the full file on GitHub · 115 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. 4d ago First seen · 115 lines · 41 tokens per session scan A b234ae06959e

Subscribe to this mod's changes

learn is a command published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 1mo ago), licensed MIT. It adds 41 tokens to every session and 1,245 once invoked, about $0.0002 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.