Starlight-Intelligence-System: Command for Claude Code

.claude/commands/perf-review-redesign.md

perf-review-redesign is a command for Claude Code from frankxai/Starlight-Intelligence-System. It costs 64 tokens per session (3,274 once invoked), scanned A, original, MIT.

A command that redesigns annual employee performance reviews into ongoing feedback, quarterly growth discussions, and separate yearly decisions about pay and promotion.

In plain words
What is it for?
Use it to produce a redesign plan, manager scripts, employee preparation guidance, calibration steps, and a transition plan.
Why use it?
It gives organizations a replacement for an annual rating process they find ineffective, while flagging legal, contract, HR-system, and privacy concerns.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is frankxai/Starlight-Intelligence-System's own configuration. It tells Claude Code how to work on Starlight-Intelligence-System itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything Starlight-Intelligence-System configures →

Part of the starlight-intelligence-system plugin — 6 skills, 121 commands, 7 agents shipped together

Reuse

Borrowing it

Nothing to install: this file belongs to frankxai/Starlight-Intelligence-System. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/frankxai/Starlight-Intelligence-System/main/.claude/commands/perf-review-redesign.md
Clone the repo
git clone --depth 1 https://github.com/frankxai/Starlight-Intelligence-System

Made for: Claude Code.

Or install starlight-intelligence-system, the plugin that ships this one along with the rest of its 6 skills, 121 commands, 7 agents.

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 perf-review-redesign

README.md
[![agentmods](https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-review-redesign/github.svg)](https://agentmods.dev/commands/frankxai/starlight-intelligence-system/perf-review-redesign)
Your own site
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/perf-review-redesign"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-review-redesign/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 perf-review-redesign

Your own site · 80×15
<a href="https://agentmods.dev/commands/frankxai/starlight-intelligence-system/perf-review-redesign"><img src="https://agentmods.dev/badge/commands/frankxai/starlight-intelligence-system/perf-review-redesign.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,274 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 $0.00064 $0.03274
Opus 5 $0.00032 $0.01637
Sonnet 5 $0.00013 $0.00655
Haiku 4.5 $0.00006 $0.00327

Measured 11d ago against content hash 33c4398e76e7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

perf-review-redesign 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 11d 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.

.claude/commands/perf-review-redesign.md · 212 lines

How it starts

The opening of the file, as written. The whole thing — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/perf-review-redesign

Load SIP.md, VOICES.md, agents/starlight-performance.md, skills/people-intelligence/feedback-conversations.md. If a Hiring sub-system calibration protocol exists at people-intelligence/hiring/calibration-*.md, read it for grammar transfer. Produce a Performance Review Redesign Plan that replaces a broken annual ritual with continuous SBI + quarterly growth + separated annual comp/promotion architecture. Save to people-intelligence/performance/redesign-<org-slug>-<date>.md.

Disclaimer (non-waivable)

This is rehearsal architecture and organizational design thinking, not legal counsel and not HRIS implementation. Changing the linkage between performance ratings and compensation touches legal documentation, employment contracts, and (in some jurisdictions) collective bargaining agreements. Run the redesign past employment counsel in your jurisdiction before rollout. Run the HRIS changes past your HRIS vendor and your data privacy officer.

Input

$ARGUMENTS

When this command fires

  • An organization has an annual rating ritual that no one finds useful but no one has dismantled
  • A founder or HR leader inherited a stack rank or forced curve and wants to know how to dismantle it without dropping the wheels off the bus
  • A 360 review process is taking 40+ hours per cycle per manager and producing thin output
  • Leadership is reading the research (Deloitte, Adobe, Microsoft, GE case studies) and wants the practitioner-grade replacement architecture

When this command does NOT fire

  • The organization is a 5-person team that has no formal review ritual at all → halt and recommend /perf-coaching-protocol for the 1:1 architecture; no redesign is needed because there's nothing to dismantle
  • The organization is a regulated industry where annual ratings are a compliance requirement (rare; usually misread) → halt; check the actual regulation with employment counsel before assuming it requires what it requires
  • The user wants a "more rigorous" stack rank or "better" forced curve → refuse; the research is unambiguous on harm. Offer the redesigned architecture instead

Read the full file on GitHub · 212 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. 11d ago First seen · 212 lines · 64 tokens per session scan A 33c4398e76e7

Subscribe to this mod's changes

perf-review-redesign is a command published in the GitHub repository frankxai/Starlight-Intelligence-System (8 stars, last pushed today), licensed MIT. It adds 64 tokens to every session and 3,274 once invoked, about $0.0003 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 2026-08-31.