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-managerial-leveragegit 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-managerial-leverage)<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/apply-managerial-leverage"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-managerial-leverage/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-managerial-leverage"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/apply-managerial-leverage.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 | $0.00082 | $0.01758 |
| Opus 5 | $0.00041 | $0.00879 |
| Sonnet 5 | $0.00016 | $0.00352 |
| Haiku 4.5 | $0.00008 | $0.00176 |
Grade A, and why
apply-managerial-leverage 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 8d 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 — 63 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Apply Managerial Leverage
Before allocating a manager's limited time to whatever feels most urgent, estimate each candidate activity's leverage — how many people's output it affects, for how long, and whether it specifically requires your position to do — because a manager's actual output is the output of the organization under their influence, not the sum of tasks they personally complete.
Why This Is Best Practice
Why best: Grove's core reframing is that a manager's own individual task completion is a poor measure of their actual output, because a manager's real contribution is realized through other people's work, not through their own direct production. This reframing has a specific, falsifiable consequence: since time is the fixed constraint, the correct allocation criterion isn't urgency or personal preference, but leverage — the size of the multiplier a given hour of managerial time has on the output of others. An hour spent training ten people who each apply that training for months afterward has vastly more leverage than an hour spent personally completing one task, even when the individual task feels more immediately productive.
Andrew S. Grove, "High Output Management" (1983): Writing from his experience as an Intel co-founder and CEO who helped scale the company into a dominant semiconductor manufacturer, Grove formalizes "managerial leverage" as a specific evaluative lens: an activity has high leverage when it affects the output of many people, when its effect persists over a long duration, or when it requires something only that manager's specific position can provide (unique information, authority, or access) — and low leverage when its output benefits only the manager individually with no multiplier through others. Grove explicitly identifies training and the timely, broad sharing of information as inherently high-leverage activities, because their effect compounds across everyone who receives them and persists over time, in contrast to routine individual task completion, which produces output only once and only for the manager.
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.
- 8d ago First seen · 63 lines · 82 tokens per session scan A 70021e97065e
apply-managerial-leverage is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 82 tokens to every session and 1,758 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.
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…
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.
deep-work-optimization
Focus blocks, distraction management, and flow state triggers for cognitively demanding work.
disagreement-protocol
Canonical phrasing for respectful disagreement without capitulation — structural resistance to sycophancy.
opt-in-workspace-writes
Extensions/tools that auto-write to user workspaces without consent.