run-performance-calibration

run-performance-calibration is a skill for Claude Code from jeffreytse/grimoire-core. It costs 40 tokens per session (1,916 once invoked), scanned A, original, MIT.

A structured meeting where managers compare employee performance ratings against a shared standard before reviews are finalized.

In plain words
What is it for?
Use it to review ratings across managers, discuss differences, and identify employees whose performance or promotion readiness needs closer discussion.
Why use it?
It helps reduce inconsistent ratings and uncover possible bias between teams. It also supports more consistent promotion and compensation decisions.

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 review ratings across managers, discuss differences, and identify employees whose performance or promotion readiness needs closer discussion.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/run-performance-calibration
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-performance-calibration
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-performance-calibration

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/run-performance-calibration"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/run-performance-calibration.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,916 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 $0.00040 $0.01916
Opus 5 $0.00020 $0.00958
Sonnet 5 $0.00008 $0.00383
Haiku 4.5 $0.00004 $0.00192

Measured 7d ago against content hash c41a0d06b127, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

run-performance-calibration 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/leadership/skills/run-performance-calibration/SKILL.md · 150 lines

How it starts

The opening of the file, as written. The whole thing — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run Performance Calibration

Facilitate a cross-manager calibration session where each manager's ratings are reviewed against a shared standard — to correct for individual rater bias, surface promotion candidates, and produce fair performance outcomes across the team.

Why This Is Best Practice

Adopted by: Google, Amazon, Microsoft, Meta, and Salesforce all run formal calibration sessions as part of their annual performance cycle; Google's re:Work program documents calibration as a required step before performance ratings are finalized; SHRM's performance management best practice guide identifies calibration as the primary mechanism for reducing rater bias at scale; the US federal government mandates performance calibration under OPM guidelines for Senior Executive Service ratings Impact: A 2019 Deloitte human capital research study found that organizations using structured calibration sessions reduced rating distribution skew by 35% compared to organizations relying on individual manager ratings alone; Google's internal research (published in re:Work) found that calibrated ratings produced 28% less variance in performance scores for comparable performers across different managers; uncalibrated ratings systematically disadvantage employees whose managers are lenient raters, those working in less visible roles, and those on teams with harsher managers Why best: Without calibration, performance ratings measure both the employee's performance and the manager's rating tendencies — a harsh rater's strong performers receive the same ratings as a lenient rater's average performers; this inequity flows directly into compensation and promotion decisions, creating retention risk among the best performers who are rated fairly only in relative terms, and advancement inequity among employees in harsher rating environments

Sources: Google re:Work "Manager Training: Performance Calibration"; Deloitte "Performance Management: Playing a Winning Hand" (2019); SHRM "Calibration Meetings: Best Practices" (shrm.org); Buckingham & Goodall "Reinventing Performance Management" (Harvard Business Review, 2015)

Read the full file on GitHub · 150 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 · 150 lines · 40 tokens per session scan A c41a0d06b127

Subscribe to this mod's changes

run-performance-calibration is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 22d ago), licensed MIT. It adds 40 tokens to every session and 1,916 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.