design-performance-review-system

design-performance-review-system is a skill for Claude Code from jeffreytse/grimoire-core. It costs 26 tokens per session (793 once invoked), scanned A, original, MIT.

A framework for replacing traditional annual reviews with a structured system of goals, feedback, development conversations, and evaluations.

In plain words
What is it for?
Use it to assess an existing review process, choose a feedback schedule, and design fair performance conversations.
Why use it?
It helps make performance discussions more timely and useful while separating employee development from pay 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 assess an existing review process, choose a feedback schedule, and design fair performance conversations.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/jeffreytse/grimoire-core/design-performance-review-system
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 design-performance-review-system
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 design-performance-review-system

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

Your own site · 80×15
<a href="https://agentmods.dev/skills/jeffreytse/grimoire-core/design-performance-review-system"><img src="https://agentmods.dev/badge/skills/jeffreytse/grimoire-core/design-performance-review-system.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 793 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 $0.00026 $0.00793
Opus 5 $0.00013 $0.00396
Sonnet 5 $0.00005 $0.00159
Haiku 4.5 $0.00003 $0.00079

Measured 8d ago against content hash cda73f423e5d, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-performance-review-system 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.

skills/business/hr/skills/design-performance-review-system/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.

Design Performance Review System

Build a structured performance evaluation framework that drives development and fair assessment.

Why This Is Best Practice

Adopted by: Deloitte, Google, Adobe, Microsoft, GE (post-stack-rank), Netflix Impact: Deloitte found 58% of executives said traditional reviews were poor use of time; after redesign saw 14% improvement in employee engagement scores. Adobe eliminated annual reviews in 2012 and cut voluntary turnover by 30%. Why best: Frequent, forward-looking feedback addresses performance in real time rather than via retrospective annual surprises. Separating development conversations from compensation decisions reduces bias and defensiveness.

Sources: Buckingham & Goodall "Reinventing Performance Management" HBR (2015); Google re:Work research; SHRM Performance Management Guidelines (2023)

Steps

  1. Audit current state — survey managers and employees on pain points with existing process; quantify time cost (hours × headcount × frequency).

  2. Choose cadence — select review frequency: continuous check-ins (weekly/biweekly), quarterly snapshots, and annual calibration. Match cadence to business velocity.

  3. Define rating dimensions — limit to 3–5 competencies per role level (e.g., impact, collaboration, growth, execution). Avoid generic trait ratings like "attitude."

  4. Design the rating scale — use 4- or 5-point behaviorally anchored scales with written descriptors for each level. Eliminate middle-point ambiguity.

  5. Separate development from compensation — run development reviews (manager + employee focused on growth) at different times than calibration sessions that determine pay and promotion.

  6. Build calibration process — convene cross-functional calibration panels to normalize ratings across teams and reduce individual manager bias.

  7. Create manager training — train all people managers on giving SBI (Situation-Behavior-Impact) feedback, conducting review conversations, and avoiding common biases (recency, halo, affinity).

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. 8d ago First seen · 63 lines · 26 tokens per session scan A cda73f423e5d

Subscribe to this mod's changes

design-performance-review-system is a skill published in the GitHub repository jeffreytse/grimoire-core (4 stars, last pushed 23d ago), licensed MIT. It adds 26 tokens to every session and 793 once invoked, about $0.0001 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.