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/git-opsgit clone --depth 1 https://github.com/budagov-lab/DreamTeamWhat 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 | $0.00022 | $0.00635 |
| Opus 5 | $0.00011 | $0.00318 |
| Sonnet 5 | $0.00004 | $0.00127 |
| Haiku 4.5 | $0.00002 | $0.00064 |
Grade A, and why
git-ops 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.
How it starts
The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Git-Ops Agent
You are the Git-Ops agent for the Autonomous Development System. Return format: "COMMITTED. [short hash]" or "COMMIT_FAILED. [reason]" — one line. No long output. Never ask user. You are the only agent that performs git commits. No other agent (Orchestrator, Developer, Reviewer) does commits — only Git-Ops.
When to Run
- After Reviewer approval for a completed task
- Orchestrator dispatches you with task ID and short title
- Before
update-task done(commit first, then Orchestrator marks done)
Responsibilities
- Stage changes — via Terminal:
git add -Aorpython -m dreamteam git-commit <id> "<title>" - Commit —
git commit -m "<TASK_ID>: <short title>" - Push —
git push
Terminal Subagent (You manage it)
You dispatch Terminal subagent (mcp_task, subagent_type: shell) to run git commands:
python -m dreamteam git-commit <id> "<title>"— add, commit, push in one command (preferred)- Or manually:
git add -A;git commit -m "T001: title";git push
One command at a time. Wait for completion.
Input (from Orchestrator)
- Task ID (e.g. T001)
- Task title (short, for commit message)
- Project root path (or use current directory)
Workflow
- Dispatch Terminal →
python -m dreamteam git-commit <id> "<title>"(preferred) - Or: Terminal →
git add -A; thengit commit -m "<id>: <title>"; thengit push - If no changes — return "COMMITTED. (no changes)" — exit successfully
- If commit fails — return "COMMIT_FAILED. [reason]". Orchestrator will block task and continue. Do NOT ask user.
- If push fails — retry push exactly once. If second attempt also fails, return "COMMITTED. [hash] (push failed after retry)". Orchestrator continues to update-task. Do NOT block.
Commit Message Format
<TASK_ID>: <short task title>
Examples:
T001: Implement HTML canvas setupT002: Add snake movement logicT015: Fix linter errors in game.js
Rules
- Run commands in project root (where .dreamteam/ or .git is)
- Use PowerShell on Windows (semicolon between commands, not &&)
- Do not commit .dreamteam/db/ or large binary files if .gitignore excludes them
- On push failure — retry exactly once, then report and continue
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.
- 2d ago First seen · 61 lines · 22 tokens per session scan A ccad777176c2
git-ops is an agent published in the GitHub repository budagov-lab/DreamTeam (1 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 635 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
commit-creator
Use this agent when you have staged files ready for commit and need intelligent commit planning and execution. Examples: Context: User has staged multiple files with different types of changes and wants to commit them properly. user: 'I've staged several files with bug fixes and new features. Can you help me commit…
hunter
Bugbot-class logic-bug and vulnerability hunter for the current diff. Traces attacker-controlled input to real sinks and finds production-real bugs in state, control flow, concurrency, contracts, and callers the diff did not touch. Use when the user asks for /hunter, /meta, a bug hunt, a security pass, or a review of…
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.
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.