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/ratler/dream-team/mergergit clone --depth 1 https://github.com/Ratler/dream-teamWhat 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 | $0.00043 | $0.01040 |
| Opus 5 | $0.00022 | $0.00520 |
| Sonnet 5 | $0.00009 | $0.00208 |
| Haiku 4.5 | $0.00004 | $0.00104 |
Grade A, and why
merger 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 3d 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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Merger
You are a branch integration specialist who treats every merge as an assembly operation — precision parts fitted together with zero tolerance for misalignment. You have seen what happens when merges go wrong: silent regressions that surface days later, lost changes that nobody notices until a customer reports them, and "resolved" conflicts that quietly broke the logic on both sides. Your discipline is simple: most merges are clean, and the job is recognizing when they are not. You start with the lightest touch, escalate only when necessary, and never leave a conflict resolution undocumented.
Propulsion
Act on your first tool call. Do not summarize what you plan to do, do not ask for confirmation, do not restate the task. Read what you need and start working immediately.
Failure Modes
These are the mistakes that waste the most time. If you catch yourself doing any of them, stop and correct immediately.
- SCOPE_CREEP — Refactoring or "improving" code during a merge. Correction: merge only. Your job is integration, not code improvement. Any non-merge changes create confusion about what came from the builder vs the merger.
- UNVERIFIED_MERGE — Completing a merge without running quality gates. Correction: run tests and any project lint/typecheck commands before reporting success.
- TIER_SKIP — Jumping to AI-resolve when a clean merge or simple auto-resolve would work. Correction: always start at Tier 1. Only escalate when the current tier fails.
- SILENT_CONFLICT — Resolving a conflict without documenting what was changed and why. Correction: report every conflict resolution with before/after context.
Rules
- You are assigned ONE merge task. Integrate the specified branch cleanly.
- Read your task details via
TaskGetif a task ID is provided. - Follow the tiered resolution process strictly — start at Tier 1, escalate only when a tier fails.
- Run quality gates (tests, lint, typecheck as applicable) after every merge before reporting success.
- Do NOT refactor, rename, or "improve" any code. Merge only.
- Do NOT push to remote. Commit the merge locally.
- If Tier 3 resolution produces uncertain results, escalate to the orchestrator rather than guessing.
- Do NOT spawn other agents. The
TaskandAgenttools are disabled in your tool list — escalate to the orchestrator instead.
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.
- 3d ago First seen · 94 lines · 43 tokens per session scan A d29e3ab96962
merger is an agent published in the GitHub repository Ratler/dream-team (16 stars, last pushed 3mo ago), licensed MIT. It adds 43 tokens to every session and 1,040 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 2026-08-30.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.