talent-team-dynamics

talent-team-dynamics is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 89 tokens per session (3,155 once invoked), scanned A, original, MIT.

A team-dynamics audit examines how a team is structured and works together, including its development stage, status relationships, dependencies, and communication patterns.

In plain words
What is it for?
It helps diagnose team structure, hierarchy, interdependence, communication problems, and the team’s current development stage.
Why use it?
It identifies the specific conditions making collaboration difficult instead of prescribing generic team-building activities.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

Part of the starlight-intelligence-system plugin — 6 skills, 121 commands, 7 agents shipped together

Good fit It helps diagnose team structure, hierarchy, interdependence, communication problems, and the team’s current development stage.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/frankxai/starlight-intelligence-system/talent-team-dynamics
Install

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.

Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 6 skills, 121 commands, 7 agents.

Wrote 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.

agentmods badge for talent-team-dynamics

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-team-dynamics/github.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/talent-team-dynamics)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/talent-team-dynamics"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-team-dynamics/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.

agentmods 80×15 button for talent-team-dynamics

Your own site · 80×15
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/talent-team-dynamics"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-team-dynamics.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 89 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,155 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00089 $0.03155
Opus 5 $0.00044 $0.01577
Sonnet 5 $0.00018 $0.00631
Haiku 4.5 $0.00009 $0.00315

Measured 7d ago against content hash 702c76c363c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

talent-team-dynamics 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 7d 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.

.claude/commands/talent-team-dynamics.md · 216 lines

How it starts

The opening of the file, as written. The whole thing — 216 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/talent-team-dynamics

Load SIP.md, VOICES.md, agents/starlight-talent.md, skills/people-intelligence/people-dynamics.md, and any prior team artifacts (people-intelligence/talent/team-*, people-intelligence/culture/). Produce a Team Dynamics Audit. Hand off to exactly one next move — usually NOT "team-building exercises."

Disclaimer (non-waivable)

This is HR system architecture, not clinical advice. When team-level distress signals suggest individual clinical territory in any team member, refer that individual to a qualified clinician. Not legal advice — interpersonal conflict that touches harassment, discrimination, or other protected-class territory requires jurisdiction-specific compliance and qualified counsel.

Input

$ARGUMENTS

Flags

  • --size <N> — team size. Hackman bounds: real teams above ~10 strain interdependence; above ~12-15 fragment into sub-teams. Single-digit teams have different dynamics from teens.
  • --tenure <weeks|months|years> — how long this team has existed in current configuration. Tuckman stage signal — newly formed teams produce different patterns from teams in their third year.
  • Optional context: observed dynamics in plain language ("two senior ICs are in chronic disagreement on technical direction and the rest of the team has stopped engaging in technical discussions" beats "the team is dysfunctional").

Process

  1. Disclaim. Open the output with the non-waivable disclaimer. Structurally first.

  2. Hackman criteria check (load-bearing). This runs FIRST. Most "team dysfunction" resolves at this layer. The five criteria:

    • Stable membership. Has membership stayed consistent for at least 6-12 months? Or is membership rotating, with people on partial allocation, or with frequent additions/departures? Unstable membership prevents team formation. People can't form a team if the people keep changing.
    • Clear bounds. Does everyone agree who is on this team and who is not? Are there shadow members (allocate 20% but show up to 80% of meetings)? Are there ghost members (named on the team but never engaged)? Unclear bounds prevent commitment.
    • Shared task. Is there a single shared outcome the team owns together? Or are these N people doing N parallel pieces of work that happen to meet in retrospectives? Co-acting groups have parallel work; real teams have shared work.
    • Interdependence. Do members actually depend on each other to complete the shared task? Or could each member's work proceed if the others stopped? If interdependence is low, the team-building intervention is wrong; clarify membership and reassign.
    • Authority over the work. Does the team have decision-making authority over how the work gets done? Or are decisions made above them and pushed down? Authority-less teams cannot form true accountability.

Read the full file on GitHub · 216 lines

Changes

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.

  1. 7d ago First seen · 216 lines · 89 tokens per session scan A 702c76c363c5

Subscribe to this mod's changes

talent-team-dynamics is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 89 tokens to every session and 3,155 once invoked, about $0.0004 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 2026-09-03.