run-exit-interview

run-exit-interview is a skill for Claude Code from jeffreytse/grimoire-core. It costs 22 tokens per session (909 once invoked), scanned A, original, MIT.

A structured process for talking with employees who are leaving, recording their reasons, and finding patterns in their feedback.

In plain words
What is it for?
Use it to plan interview questions, conduct exit interviews, and turn departing employees’ comments into retention actions.
Why use it?
It helps replace scattered or overly polite feedback with comparable information about why people leave and what the organization could improve.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the grimoire-business plugin — 145 skills shipped together

Good fit Use it to plan interview questions, conduct exit interviews, and turn departing employees’ comments into retention actions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/run-exit-interview
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.

Any agent
npx skills add jeffreytse/grimoire-core --skill run-exit-interview
Clone the repo
git clone --depth 1 https://github.com/jeffreytse/grimoire-core

Made for: Claude Code.

Or install grimoire-business, the plugin that ships this one along with the rest of its 145 skills.

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 run-exit-interview

README.md
[![agentmods](https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-exit-interview/github.svg)](https://agentmods.dev/skills/jeffreytse/grimoire-core/run-exit-interview)
Your own site
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-exit-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-exit-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.

agentmods 80×15 button for run-exit-interview

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-exit-interview"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-exit-interview.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 909 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 $0.00022 $0.00909
Opus 5 $0.00011 $0.00454
Sonnet 5 $0.00004 $0.00182
Haiku 4.5 $0.00002 $0.00091

Measured 9d ago against content hash c08a13e4f06c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

run-exit-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 9d 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.

skills/business/hr/skills/run-exit-interview/SKILL.md · 63 lines

How it starts

The opening of the file, as written. The whole thing — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Exit Interview

Conduct a structured exit interview that surfaces actionable retention insights from departing employees.

Why This Is Best Practice

Adopted by: LinkedIn, Deloitte, McKinsey, and organizations with mature people analytics functions Impact: Work Institute (2020) found 77% of employee turnover is preventable; organizations that act on exit interview data reduce voluntary attrition by 10–25%. HBR research shows most companies collect exit data but only 4% systematically use it. Why best: Departing employees often share candid feedback they withheld while employed. Aggregated exit data identifies systemic issues (management quality, compensation gaps, career ceiling) that engagement surveys underreport due to social desirability bias.

Sources: Garvin "Making Exit Interviews Count" HBR (2008); Work Institute "Workforce Retention Report" (2020); SHRM Exit Interview Best Practices (2022)

Steps

  1. Decide the interviewer — never have the direct manager conduct the exit interview. Use HR, a skip-level, or an independent third party. Departing employees are less candid with their own manager.

  2. Schedule promptly — conduct within the last week of employment. Earlier risks the employee not yet being candid; later risks memory degradation and declining willingness.

  3. Set the context — open by explaining the purpose: the conversation is confidential, feedback improves the organization for current employees, and no response will affect references or final pay.

  4. Use a structured question set — cover: reason for leaving, job satisfaction, manager relationship, team culture, compensation competitiveness, career development opportunities, and what would have caused them to stay.

  5. Ask the "stay question" — "What could we have done differently to retain you?" This is the single highest-signal question. Probe the first answer: "What else?"

  6. Explore the new opportunity — ask about the new role (function, company size, industry, compensation). This reveals where talent is going and what pulls employees away.

Read the full file on GitHub · 63 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. 9d ago First seen · 63 lines · 22 tokens per session scan A c08a13e4f06c

Subscribe to this mod's changes

run-exit-interview is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 24d ago), licensed MIT. It adds 22 tokens to every session and 909 once invoked, about $0.0001 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.