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.
npx agentmods add commands/bondarewicz/dreamteam/learngit clone --depth 1 https://github.com/bondarewicz/dreamteamWrote 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.
[](https://agentmods.dev/commands/bondarewicz/dreamteam/learn)<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>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00041 | $0.01245 |
| Opus 5 | $0.00020 | $0.00622 |
| Sonnet 5 | $0.00008 | $0.00249 |
| Haiku 4.5 | $0.00004 | $0.00125 |
Grade A, and why
learn scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Dream Team Learning Loop for this session. Your job is to run the end-of-session
learning step — the same step the team.md SESSION LEARNING (DB LOOP) section runs at the end of a
/team session — adapted for ordinary (non-/team) Claude Code sessions.
The CLI is the single behavioral gate. All scrub, confidence, AC-8 self-check, consent rules, and
projection determinism live in dreamteam learn (runLearn in bin/dreamteam.ts). Do not re-author
any of that logic here.
Pre-cutover safe:
dreamteam learnwrites to the Dream Team workspace (~/.dreamteam/workspace/memory/<project>/) by default — it does NOT touch~/.claude. TheisUnderClaudeDirguardrail refuses~/.claudewithout--installer-phase, which is only set by the slice-9 cutover script. Running/learntoday is safe and reversible.
STEP 1 — Run the analyzer + approve auto-inferred pending
Invoke dreamteam learn in the current project directory:
dreamteam learn --project "$(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:
- ensure — idempotent DDL; no-op if tables already exist
- analyze — session analyzer reads recent eval findings; materializes candidate instincts
- approve auto-inferred pending — prompts
Approve instinct #id [domain]: "trigger" (conf X.XX)? [y/N]per auto-inferred pending row. Answeryorn— no free text required. Human-directive rows are NOT presented here (they require the authorship act, Step 2). - 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:
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.
- 4d ago First seen · 115 lines · 41 tokens per session scan A b234ae06959e
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.
Other commands, from other repositories
resume
Resume a previous session. Reads recent session logs, open tasks, and last decisions — gives Claude full context without re-explaining the project.
notebook
Low-ceremony capture for ideas (half-formed, want to mature into stories), todos (concrete actions), and notes (durable project/team facts for future recall). One-line capture, conditional elaboration AUQ. Use BEFORE thoughts get forced into stories.
end-session
Wrap up the work session with read-only evidence gathering, owner-classified documentation handoffs, gated issue sync, Kano refinement, and git hygiene checks.
wb-email-triage
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "email/triage-directions", "depth": "full"}), then run the workflow.
wb-session-identify
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "context/session-identify", "depth": "full"}), then follow the procedure with $ARGUMENTS as the user's handoff (topic, time window, keywords, known false positives).
wb-morning
Load directions via mcpwork-buddywbrun("agentdocs", {"path": "morning/directions", "depth": "full"}), then run the workflow.