talent-psych-safety

talent-psych-safety is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 79 tokens per session (3,331 once invoked), scanned A, original, MIT.

A psychological-safety measurement plan uses an anonymous seven-question survey over time to understand whether team members feel safe speaking up, asking questions, and taking interpersonal risks.

In plain words
What is it for?
It helps establish a baseline, track changes across repeated surveys, interpret results, and design follow-up actions focused on leader behavior.
Why use it?
It avoids treating one survey score or a standalone training session as a complete diagnosis of team safety.

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 establish a baseline, track changes across repeated surveys, interpret results, and design follow-up actions focused on leader behavior.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/talent-psych-safety"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-psych-safety.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 79 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,331 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 $0.00079 $0.03331
Opus 5 $0.00039 $0.01665
Sonnet 5 $0.00016 $0.00666
Haiku 4.5 $0.00008 $0.00333

Measured 8d ago against content hash ac03538fc7ac, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

talent-psych-safety 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 8d 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-psych-safety.md · 226 lines

How it starts

The opening of the file, as written. The whole thing — 226 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/talent-psych-safety

Load SIP.md, VOICES.md, agents/starlight-talent.md, skills/people-intelligence/people-dynamics.md, prior team-dynamics audits if any (people-intelligence/talent/team-dynamics-*), and Culture artifact for system-context (people-intelligence/culture/). Produce a Psychological Safety Measurement Plan plus interpretation rubric plus intervention design (if measuring follow-up). Hand off to exactly one next move.

Disclaimer (non-waivable)

This is HR system architecture, not clinical advice. When safety signals reveal individual distress crossing into clinical territory, refer that individual to a qualified mental health clinician. Not legal advice — patterns of fear-based silence around harassment, discrimination, or retaliation require jurisdiction-specific compliance and qualified counsel; this command does not resolve such legal matters.

Input

$ARGUMENTS

Flags

  • --baseline-or-followup <baseline|followup> — first measurement establishes baseline; subsequent measurements track shift. Single-snapshot psych-safety scoring is refused — the construct is longitudinal.
  • --prior-survey-date <YYYY-MM-DD or none> — when was the last measurement, if any. Use to assess shift if followup.
  • Optional context: what triggered the measurement (manager observation, recent silence pattern, post-reorg check, quarterly cadence).

Process

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

  2. Cite the research foundation. Edmondson 1999 onward: psychological safety as the shared belief that the team is safe for interpersonal risk-taking. Project Aristotle (Google, 2012-2015): psychological safety the #1 predictor of team performance, above tenure, talent density, and tooling. Team-by-team variance is enormous within a single company; aggregate is misleading.

  3. Edmondson 7-question scale — administered anonymously, individually, with no individual identifiers traceable. Items (worded as common in published research; phrasing may be light-adapted to context but construct must be preserved):

Read the full file on GitHub · 226 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. 8d ago First seen · 226 lines · 79 tokens per session scan A ac03538fc7ac

Subscribe to this mod's changes

talent-psych-safety is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 79 tokens to every session and 3,331 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.