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 jeffreytse/grimoire-core --skill run-stay-interviewgit clone --depth 1 https://github.com/jeffreytse/grimoire-coreWrote 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/jeffreytse/grimoire-core/run-stay-interview)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-stay-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-stay-interview/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/jeffreytse/grimoire-core/run-stay-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-stay-interview.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 | $0.00049 | $0.01867 |
| Opus 5.5 | $0.00020 | $0.00747 |
| Sonnet 5.5 | $0.00010 | $0.00373 |
| Haiku 4.5 | $0.00005 | $0.00187 |
Grade A, and why
run-stay-interview 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 1mo 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 — 126 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Run Stay Interview
Conduct a structured, proactive conversation with a valued direct report to learn what keeps them engaged and what might drive them to leave — so you can act on that information before a resignation forces a reactive response.
Why This Is Best Practice
Adopted by: Kaye & Jordan-Evans's "Love 'Em or Lose 'Em" is the most widely cited employee retention framework, used in training programs at Boeing, the US Army, and hundreds of large corporations; SHRM's 2016 guidance identifies stay interviews as the highest-ROI single retention intervention; Microsoft, LinkedIn, and Deloitte have formalized stay interviews as part of their talent management cadence Impact: Gallup's 2017 "State of the American Workplace" found that 52% of voluntarily exiting employees say their manager or organization could have done something to prevent their departure — and 51% say no one asked them in the 3 months before they quit what would keep them; SHRM research found that replacing an employee costs 50–200% of annual salary; Kaye's research found that stay interview participants who received follow-through on at least one issue showed 40% higher retention at 12 months compared to those who received no follow-through Why best: Exit interviews collect data after the organization has already lost — the employee has resigned, is mentally gone, and has no incentive to be fully candid; performance reviews are evaluative and backward-looking; one-on-ones are operational; stay interviews are the only tool designed specifically to surface what the employee values and what they might need, while there is still time to respond
Sources: Kaye & Jordan-Evans "Love 'Em or Lose 'Em" (Berrett-Koehler, 2014); SHRM "Stay Interviews: A Tool to Prevent Employee Turnover" (shrm.org, 2016); Gallup "State of the American Workplace" (2017)
Steps
1. Determine who to interview and when
Stay interviews are not for the whole team simultaneously. Prioritize:
High priority:
- High performers who are hard to replace
- Employees who have been approached by competitors
- Employees who have recently lost a peer they were close to
- Employees with 2–4 years of tenure (high flight-risk window)
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.
- 1mo ago First seen · 126 lines · 49 tokens per session scan A 07d5653961f1
run-stay-interview is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 49 tokens to every session and 1,867 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 2026-09-03.
Other skills, from other repositories
saga-orchestration
Implement saga patterns for distributed transactions and cross-aggregate workflows. Use this skill when implementing distributed transactions across microservices where 2PC is unavailable, designing compensating actions for failed order workflows that span inventory, payment, and shipping services, building…
deep-work-optimization
Focus blocks, distraction management, and flow state triggers for cognitively demanding work.
make-skill-template
Create new Agent Skills for GitHub Copilot from prompts or by duplicating this template. Use when asked to "create a skill", "make a new skill", "scaffold a skill", or when building specialized AI capabilities with bundled resources. Generates SKILL.md files with proper frontmatter, directory structure, and optional…
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
disagreement-protocol
Canonical phrasing for respectful disagreement without capitulation — structural resistance to sycophancy.
fix-once-auto-inject
One-time fixes get repeated manually.