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 apply-high-performer-retentiongit 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/apply-high-performer-retention)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-high-performer-retention"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-high-performer-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/skills/jeffreytse/grimoire-core/apply-high-performer-retention"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-high-performer-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 | $0.00042 | $0.02399 |
| Opus 5 | $0.00021 | $0.01200 |
| Sonnet 5 | $0.00008 | $0.00480 |
| Haiku 4.5 | $0.00004 | $0.00240 |
Grade A, and why
apply-high-performer-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 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.
How it starts
The opening of the file, as written. The whole thing — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply High-Performer Retention
Proactively retain your highest-performing direct reports through differentiated management — providing the stretch, recognition, visibility, and honest career investment that high performers require and that uniform management approaches fail to deliver.
Why This Is Best Practice
Adopted by: Gallup's research foundation for "First Break All the Rules" (the largest workplace study ever conducted at the time — 80,000 managers, 1M employees) identified the manager relationship as the primary driver of high-performer retention; McKinsey's "War for Talent" research (first published 2001, updated multiple times through 2022) is the management consulting industry's foundational work on talent retention and is taught in executive programs at HBS and Stanford; Kaye & Jordan-Evans's "Love 'Em or Lose 'Em" is the most widely cited practitioner guide for manager-level retention practices, used in HR programs at Cisco, Marriott, and Boeing Impact: McKinsey's 2022 update to "War for Talent" research found that high performers are 400–800% more productive than average performers in complex knowledge roles — making the departure of one high performer equivalent to losing 4–8 average performers in output; Gallup research consistently finds that 70% of employees leave managers, not companies — and that high performers, who have more external options, are more likely to test the market and act on the comparison; LinkedIn's "Workplace Learning Report" (2019, 2,700 hiring managers) found that the top reason high performers left their jobs was "limited opportunity to advance" — which is a manager-level controllable, not an organizational inevitability; the cost of replacing a high performer is estimated at 150–200% of their annual compensation (SHRM), making proactive retention dramatically cheaper than replacement Why best: High performers who are being uniformly managed — given the same attention, recognition, and growth opportunities as average performers — are being under-managed in the ways that matter most to them; they are capable of more than they're being given, and they know it; they have more options than average performers, and they know that too; the manager who treats everyone identically in the name of fairness is disproportionately losing their most valuable people, while retaining those who have fewer options
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.
- 7d ago First seen · 130 lines · 42 tokens per session scan A 2003640439da
apply-high-performer-retention is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 42 tokens to every session and 2,399 once invoked, about $0.0002 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 skills, from other repositories
employee-engagement-retention
Provides a practical, behaviour-level guide to why employees stay, why they leave, and what leaders do daily that determines which outcome occurs. Covers the eight retention-destroying behaviours, recognition versus appreciation, purpose-building, learning as a retention lever, and structured check-in practices that…
org-report
Generate an executive organization brief (leadership chain, direct reports, extended teams, and vendor partners) for a target person. Produces a Word + PDF report from a directory MCP source (WorkIQ is the reference implementation) and displays it in a Copilot canvas. Triggers on "generate org report for X", "build…
coaching-techniques
GROW model, active listening, developmental feedback, and team growth approaches.
meeting-efficiency
Agenda design, time boxing, decision capture, async alternatives, and productive facilitation.
stakeholder-management
Influence mapping, communication strategies, and expectation management for complex organizations.
scaffolding-generator
Pattern-aware code scaffolding that detects existing conventions and generates new components matching the codebase style. Use when asked to "scaffold a component", "generate boilerplate", "create a new module", "bootstrap a service", "add a new endpoint", "create a new controller", or "add a new feature module".…