apply-gilded-retirement

apply-gilded-retirement is a skill for Claude Code from jeffreytse/grimoire-core. It costs 86 tokens per session (2,050 once invoked), scanned A, original, MIT.

A strategy for persuading a powerful colleague or subordinate to give up an independent power base voluntarily by offering security, status, and rewards.

In plain words
What is it for?
It helps plan leadership transitions, organisational restructuring, and negotiations with people whose influence could challenge the current leadership.
Why use it?
It reduces the risk of conflict, defection, or reputational damage that can follow a direct purge or confrontation.

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 It helps plan leadership transitions, organisational restructuring, and negotiations with people whose influence could challenge the current leadership.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/apply-gilded-retirement
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-gilded-retirement
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 apply-gilded-retirement

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-gilded-retirement"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-gilded-retirement.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 86 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,050 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 $0.00086 $0.02050
Opus 5 $0.00043 $0.01025
Sonnet 5 $0.00017 $0.00410
Haiku 4.5 $0.00009 $0.00205

Measured 7d ago against content hash abf86250fcdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

apply-gilded-retirement 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.

skills/business/strategy/skills/apply-gilded-retirement/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Apply Gilded Retirement

When a subordinate or peer has accumulated dangerous, independent power, make voluntary relinquishment strictly more attractive than retention — paying with wealth, status, and security — rather than confronting or purging them and risking open conflict.

Why This Is Best Practice

Origin: In 960 AD, Zhao Kuangyin seized the Song throne with the backing of the military, well aware that the same mechanism — a general commanding the personal loyalty of his troops — could just as easily be turned against him. In 961 AD, he hosted a banquet for his most senior generals, including Shi Shouxin, who held the very command Zhao himself had used to seize power. Rather than purging them as the obvious threats they were, Zhao proposed they voluntarily surrender their military commands in exchange for large estates, honorary titles, wealth, and marriage alliances binding their families to his. Every general accepted. The transition was bloodless, and it removed the exact structural threat — regional generals with independent troop loyalty — that had made the founding of the dynasty possible in the first place, without a single purge, execution, or armed confrontation.

Adopted by: The mechanism recurs directly in modern corporate governance under the "golden parachute" umbrella: a board facing an entrenched, powerful executive or co-founder offers a generous exit package — cash, equity acceleration, a face-saving title, continued board visibility — specifically to make voluntary departure more attractive than a fight for control. Its use in removing founder-CEOs with entrenched board or voting control, rather than forcing a proxy fight or hostile ouster, is a standard modern playbook, most visibly used when the person holds informal power (loyalty of key staff, brand identity, voting control) that a formal removal vote alone would not neutralize.

Impact: The Song banquet is documented to have permanently ended the pattern of regional military governors (節度使) accumulating troop loyalty strong enough to challenge the throne — a structural threat that had repeatedly toppled prior dynasties — without a single execution, exile, or armed clash. Lambert & Larcker's empirical research on golden parachutes documents the mechanism's modern equivalent: boards using generous negotiated exit packages measurably reduce the incidence of costly proxy fights and hostile removal battles compared to attempting to strip an entrenched executive of power directly.

Read the full file on GitHub · 66 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. 7d ago First seen · 66 lines · 86 tokens per session scan A abf86250fcdc

Subscribe to this mod's changes

apply-gilded-retirement is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 86 tokens to every session and 2,050 once invoked, about $0.0004 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.