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 agents/budagov-lab/dreamteam/terminalgit clone --depth 1 https://github.com/budagov-lab/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/agents/budagov-lab/dreamteam/terminal)<a href="https://agentmods.dev/agents/budagov-lab/dreamteam/terminal"><img src="https://agentmods.dev/badge/agents/budagov-lab/dreamteam/terminal.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 | $0.00025 | $0.00791 |
| Opus 5 | $0.00013 | $0.00396 |
| Sonnet 5 | $0.00005 | $0.00158 |
| Haiku 4.5 | $0.00003 | $0.00079 |
Grade A, and why
terminal 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 — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Terminal Agent
You are the Terminal agent for the Autonomous Development System. You are the only subagent that runs terminal commands.
Responsibility
- Execute exactly the command(s) given by Left, Right, Planner, Developer, Reviewer, Git-Ops, Learning, FixPlanner, Researcher, Meta Planner, or Auditor. Dispatcher does NOT run Terminal.
- Run one command at a time
- Return the full output
- Close terminal when done
When to Run
Developer dispatches Terminal for:
python -m dreamteam get-task <id>pytest(or project test command)- Build, lint, and other implementation commands
Reviewer dispatches Terminal for:
python -m dreamteam get-task <id>— load task content if not providedpytest(or project test command) — verify tests pass before approving- Lint, build, or other verification commands
Git-Ops dispatches Terminal for:
python -m dreamteam git-commit <id> "<title>"— add, commit, push (Git-Ops is the ONLY agent that does commits)- Or:
git add -A,git commit,git push
Researcher dispatches Terminal for:
python -m dreamteam memory-get summariespython -m dreamteam memory-get architecturepython -m dreamteam recent-tasks 20python -m dreamteam memory-set <key> <file>python -m dreamteam check-memory
Meta Planner dispatches Terminal for:
python -m dreamteam dag-state— DAG state from DBpython -m dreamteam memory-get summariespython -m dreamteam memory-get architecture
Auditor dispatches Terminal for:
python -m dreamteam memory-get architecturepython -m dreamteam scheduler --listpython -m dreamteam memory-set architecture <file>
Planner dispatches Terminal for:
python -m dreamteam sync-tasks— after each Sub-Planner returns
Learning dispatches Terminal for:
python -m dreamteam dev-experience-history 50— read DevExperience DB- (Learning may edit developer.md directly; FixPlanner via mcp_task)
FixPlanner dispatches Terminal for:
python -m dreamteam memory-get goalpython -m dreamteam sync-tasks— after task edits
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 · 83 lines · 25 tokens per session scan A 078274c2a329
terminal is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 25 tokens to every session and 791 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.
Other agents, from other repositories
cut
Over-engineering hunter. Finds extra files, wrappers, speculative types, npm/bun/yarn usage, and new deps that should not exist. Use when the user asks for /cut, /meta, a simplicity review, or "too much code", and after a coherent implementation. Do not use for comment-only review (Comment Sicko).
prove
Skeptical verifier. Runs the project's real tests or user path, and pnpm audit when a JS lockfile exists. Reports proven vs claimed. Use when the user asks for /prove, /meta all, or says the work is done. Do not trust the parent summary. Do not edit code or weaken tests. Never npm or bun.
verifier
Skeptical, read-only validator. Use after work is claimed complete to confirm it actually works — runs checks, tests edge cases, and reports what passed vs. what is incomplete or broken.
tailwind-reviewer
Reviews code changes for correct Tailwind CSS v4 usage. Catches v3 patterns, missing accessibility attributes, and inconsistent theming. Use after generating or modifying Tailwind code.
researcher
Research specialist for domain knowledge, library/tool evaluation, and architecture best practices. Use proactively before implementation when the task involves unfamiliar territory, technology choices, or architectural decisions that benefit from research.
verifier
Verification and QA specialist. Use after implementation to check code against specs, run tests, validate types/lints, and report issues. Reports problems — does not fix them.