apply-talent-density-culture

apply-talent-density-culture is a skill for Claude Code from jeffreytse/grimoire-core. It costs 90 tokens per session (1,655 once invoked), scanned A, original, MIT.

A method for deciding whether a team member's performance is strong enough to retain. It asks whether you would make a serious effort to keep them if they were leaving for a similar job.

In plain words
What is it for?
Use it in ongoing performance reviews, team staffing decisions, and discussions about retaining or replacing employees.
Why use it?
Accepting adequate performance indefinitely can weaken a team and make poor fit harder to address. The method encourages clearer retention and departure decisions.

Skill for Claude Code

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

Part of the grimoire-business plugin — 156 skills shipped together

Good fit Use it in ongoing performance reviews, team staffing decisions, and discussions about retaining or replacing employees.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-talent-density-culture
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 apply-talent-density-culture
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 156 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 apply-talent-density-culture

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-talent-density-culture"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-talent-density-culture.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 90 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,655 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 $0.00090 $0.01655
Opus 5.5 $0.00036 $0.00662
Sonnet 5.5 $0.00018 $0.00331
Haiku 4.5 $0.00009 $0.00166

Measured 4d ago against content hash bcb4a5709115, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

apply-talent-density-culture 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 4d 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/apply-talent-density-culture/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.

Apply Talent Density Culture

Apply the keeper test — would you fight hard to keep this person if they told you they were leaving for a similar role elsewhere? — to every team member's ongoing performance, instead of tolerating adequate-but-not-exceptional performance indefinitely, pairing fast departures with generous severance and above-market pay for those who pass, because a team of only high performers coordinates and executes at a level an average-performer team cannot reach regardless of added process or headcount.

Why This Is Best Practice

Hastings & Meyer, "No Rules Rules" (2020): Documents Netflix's deliberate rejection of "adequate performance" as sufficient in a high-density team. Managers are asked to periodically apply the keeper test to every direct report; anyone who fails it receives a generous, promptly-delivered severance package rather than being cycled through an extended performance-improvement process. Netflix pairs this standard with paying retained top performers meaningfully above market rate, on the premise that talent density (not process, perks, or headcount) is what let a lean team consistently out-execute much larger competitors.

Isaacson, "Steve Jobs" (2011): Documents Jobs' parallel conviction, applied at Apple across four decades: keep product teams deliberately small and staffed only with people considered top-tier, because "A players hire A players; B players hire C players" — diluting a team with adequate performers compounds downward across subsequent hiring rounds as those performers hire to their own level rather than above it.

Why best: Standard performance-review cycles are built to distinguish "meets expectations" from "underperforms," and tend to leave adequate performers in place indefinitely once they clear that bar. The keeper test asks a different, harder question — not "is this performance acceptable" but "would losing this person to a competitor genuinely hurt" — which surfaces the specific cost of adequate performance in a role an exceptional performer could otherwise fill.

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. 4d ago First seen · 63 lines · 90 tokens per session scan A bcb4a5709115

Subscribe to this mod's changes

apply-talent-density-culture is a skill published in the GitHub repository jeffreytse/grimoire-core (5 stars, last pushed 5d ago), licensed MIT. It adds 90 tokens to every session and 1,655 once invoked, about $0.0004 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 2026-10-17.