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 skills/haoruilee/oh-my-mcode/teamnpx skills add haoruilee/oh-my-mcode --skill teamgit clone --depth 1 https://github.com/haoruilee/oh-my-mcodeWhat 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 | $0.00118 | $0.00612 |
| Opus 5 | $0.00059 | $0.00306 |
| Sonnet 5 | $0.00024 | $0.00122 |
| Haiku 4.5 | $0.00012 | $0.00061 |
Grade A, and why
team 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.
What it actually says
Team
Explicit flat team. Sequential max stays the default. Project-manager duties stay in TypeScript. Do not spawn grandchild agents.
This skill does not register host /team. Desktop /team remains the host's Agent Team.
中文名：扁平团队。
Inputs
- Task / goal.
- Prefer
oh-my-mcode team "<task>"oroh-my-mcode max --team "<task>". - MCP first: if
omm_*tools exist, use them instead of hand-writing run files. Parallel worktrees may use their own host session (different cwd); the parent run session stays on the workspace. - Optional
--worktree(git worktree per parallel builder under.minimax/worktrees/<run>/<task>). - Concurrency default 2.
Procedure
- Same INTAKE → DISCOVER → PLAN as
max, but the planner DAG may include independent builders. - The CLI orchestrator schedules ready builders (no unsatisfied deps) in parallel
mcode execworkers. You do not spawn children. - Optional worktree: merge back only after that task's verify slice passes. Clean up on cancel.
- VERIFY remains a separate phase. Builders never mark Accepted.
- Bound concurrency. No 1100-line Sisyphus loop.
Output contract
- Same run store as
max.team_spawnedevents when a parallel wave starts. - Verifier writes Accepted / Rejected.
Failure handling
- Shared-file conflicts without
--worktree: stop and ask for worktrees or a sequentialmax. - Host
/teamrequested: explain coexistence; use this skill only for a durable oh-my-mcode run.
Examples
User: oh-my-mcode team: implement logging and docs if they do not share files
Use the team CLI. Independent builders may run in parallel.
User: /team in the MiniMax desktop
Host feature. Do not claim we registered it.
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 · 57 lines · 118 tokens per session scan A ceab6453b375
team is a skill published in the GitHub repository haoruilee/oh-my-mcode (51 stars, last pushed 4d ago), licensed MIT. It adds 118 tokens to every session and 612 once invoked, about $0.0006 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 skills, from other repositories
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
omni-mcp
Connect to the OmniRoute MCP server (110 tools, 3 transports: SSE/stdio/HTTP). Covers routing, cache, compression, memory, skills, providers, and audit tools across 33 permission scopes.
add-resend
Add Resend (email) channel integration via Chat SDK.
codegen
Code generation utilities for json-render. Use when generating code from UI specs, building custom code exporters, traversing specs, or serializing props for @json-render/codegen.
agui-dotnet-sample-step
Add a GettingStarted sample Step (a Server/Client pair) to the AG-UI .NET SDK that demonstrates one protocol feature the way we want users to write it. USE FOR: adding a new samples/GettingStarted/StepNN Server+Client pair, wiring it into AGUI.slnx and the integration-test project, giving it a deterministic…
optimize-agentic-workflow
Analyze and reduce token consumption in agentic workflows — guardrail-specific entry points, measurement, and optimization techniques.