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 skills add josix/agent-flow --skill team-decisiongit clone --depth 1 https://github.com/josix/agent-flowWrote 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/skills/josix/agent-flow/team-decision)<a href="https://agentmods.dev/skills/josix/agent-flow/team-decision"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/team-decision/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/josix/agent-flow/team-decision"><img src="https://agentmods.dev/badge/skills/josix/agent-flow/team-decision.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.02118 |
| Opus 5.5 | $0.00016 | $0.00847 |
| Sonnet 5.5 | $0.00008 | $0.00424 |
| Haiku 4.5 | $0.00004 | $0.00212 |
Grade A, and why
team-decision 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 24d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Team Decision
Deprecated: Agent Teams via
/team-orchestrateis deprecated — the TeamCreate/TeamDelete/TaskCreate/TaskUpdate tools were removed from Claude Code (every session now has one implicit team). Prefer/orchestrate, which already runs agents in the background. The independence and cost-benefit criteria below still apply when deciding whether to dispatch agents in parallel within/orchestrate.
Overview
The team decision skill guides the choice between parallel Agent Teams execution and sequential subagent orchestration. This skill analyzes task characteristics to determine whether parallel execution is safe, beneficial, and cost-effective.
Owner Agent: Senku (Planner Agent)
Consumers: Orchestrator (primary decision maker)
Key Principles
- Safety First: Only parallelize when tasks are truly independent
- Cost-Benefit Analysis: Parallel overhead must be justified by time savings
- File Ownership: Exclusive file ownership prevents conflicts
- Fail to Sequential: When in doubt, use sequential orchestration
When to Use This Skill
Apply team decision analysis when:
- A task naturally decomposes into multiple subtasks
- Subtasks could potentially run in parallel
- Time-to-completion is a priority
- Determining whether to spawn a team or orchestrate sequentially
Decision Criteria Table
| Criterion | Use Teams (Parallel) | Use Sequential |
|---|---|---|
| Task Independence | No shared state or files | Tasks have dependencies |
| File Ownership | Exclusive file sets | Overlapping file sets |
| Parallelism Safety | Safe or Moderate | Risky |
| Number of Tasks | 2-4 independent tasks | 1 task or 5+ tasks |
| Time Sensitivity | High (user waiting) | Low (can afford serial) |
| Coordination Cost | Low (simple merge) | High (complex merge) |
| Risk Tolerance | High (can retry) | Low (must be correct) |
Quick Decision Flowchart
Task Decomposition Available?
|
+-- NO --> Sequential (single agent)
|
+-- YES
|
v
Subtasks Share Files?
|
+-- YES --> Sequential (conflict risk)
|
+-- NO
|
v
Subtasks Have Dependencies?
|
+-- YES --> Sequential (ordering required)
|
+-- NO
|
v
2-4 Subtasks?
|
+-- NO --> Sequential (too few or too many)
|
+-- YES
|
v
Time Savings > Overhead?
|
+-- YES --> TEAMS (Parallel)
|
+-- NO --> Sequential
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 24d ago Changed · +3 lines 38a8d10a83a6
- 1mo ago First seen · 303 lines · 39 tokens per session scan A 48f866ab381d
team-decision is a skill published in the GitHub repository josix/agent-flow (8 stars, last pushed 6d ago), licensed MIT. It adds 39 tokens to every session and 2,118 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
shogun-bloom-config
An interactive wizard that creates model-routing settings from your AI subscription choices. Model routing decides which available model handles each kind of task.
shogun-model-list
A reference table of AI command-line tools, their available models, subscription requirements, and maximum Bloom capability levels. Bloom's Taxonomy is a scale describing thinking tasks, from remembering information to creating new designs.
shogun-model-switch
A live-switching tool for changing which command-line AI agent, model, and reasoning mode is running. It updates settings, restarts the agent, and refreshes the displayed session information.
shogun-screenshot
A screenshot tool for getting images from a computer or web page and then cropping, resizing, or masking sensitive information. Playwright is a browser-automation tool used here to capture web pages.
shogun-readme-sync
A skill that compares an English README with its Japanese counterpart and brings them back into alignment. A README is the project document that explains what the software is and how to use it.
shogun-agent-status
A skill that shows whether the agents in a multi-agent Japanese feudal-themed team are working, waiting, missing, or assigned tasks. It combines terminal session status, task files, and unread messages.