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.
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-SystemWrote 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/commands/frankxai/starlight-intelligence-system/talent-retention)<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/talent-retention"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-retention/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/commands/frankxai/starlight-intelligence-system/talent-retention"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/talent-retention.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 | $0.00096 | $0.03226 |
| Opus 5 | $0.00048 | $0.01613 |
| Sonnet 5 | $0.00019 | $0.00645 |
| Haiku 4.5 | $0.00010 | $0.00323 |
Grade A, and why
talent-retention 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 6d 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 — 228 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/talent-retention
Load SIP.md, VOICES.md, agents/starlight-talent.md, skills/people-intelligence/people-dynamics.md, prior motivation maps and burnout detections (people-intelligence/talent/), Culture artifact for system context, Performance artifacts for calibration context, Genius Profile for voice samples in the stay-interview script. Produce a Retention Architecture — stay-interview script + per-person leverage + aggregate pattern + system redesign request. Hand off to exactly one next move.
Disclaimer (non-waivable)
This is HR system architecture, not clinical advice. When stay interviews surface individual distress crossing into clinical territory, refer that individual to a qualified clinician. Not legal advice — retention conversations touching compensation, promotion, ADA accommodations, or protected-class considerations require jurisdiction-specific compliance and qualified counsel.
Input
$ARGUMENTS
Flags
--cohort-size <N>— number of high-performers in the cohort. Realistic upper bound for one retention review: 5-15 people. Larger cohorts run as multiple smaller reviews.--org-context <consultancy|product-co|agency|other>— shapes which retention drivers tend to dominate. Consultancies: utilization + travel + project variety. Product cos: scope + technical autonomy + growth path. Agencies: client variety + creative autonomy + craft growth.- Optional context: recent attrition signals, recent voluntary departures, or what triggered the review.
Process
-
Disclaim. Open the output with the non-waivable disclaimer. Structurally first.
-
Cite the research foundation. Beverly Kaye's stay-interview research ("Love 'Em or Lose 'Em") + retention-driver meta-analyses. The structural finding: engagement surveys correlate weakly with actual retention. The real predictors are manager relationship quality, growth trajectory visibility, sense-of-fairness (SCARF), commute/flexibility fit, and life-stage fit. Stay interviews predict retention; exit interviews lag the decision and the leverage is gone.
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.
- 6d ago First seen · 228 lines · 96 tokens per session scan A 8e016f1b218e
talent-retention is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 96 tokens to every session and 3,226 once invoked, about $0.0005 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.
Other commands, from other repositories
lavra-checkpoint
Save session progress by filing beads, capturing knowledge, and syncing state.
bigproject
Large-scale project orchestration with Himawari (Atlas).
memories
View and manage learned memories.
mpm-init
Initialize or update project for Claude Code and MPM.
mpm-organize
Organize project files with intelligent consolidation.
mpm-ticket-view
Orchestrate ticketing agent for project management workflows.