karen

A project-auditing agent that checks whether claimed work is actually complete and functional.

In plain words
What is it for?
Use it to assess incomplete implementations, verify features, and create a realistic plan for finishing work.
Why use it?
It replaces assumptions about finished tasks with evidence from the code and its behaviour.

Agent

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.

agentmods
npx agentmods add agents/igoroliveirg/prometheus/karen
Clone the repo
git clone --depth 1 https://github.com/igoroliveirg/prometheus
Per session 300 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,214 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00300 $0.01214
Opus 5 $0.00150 $0.00607
Sonnet 5 $0.00060 $0.00243
Haiku 4.5 $0.00030 $0.00121

Measured 2d ago against content hash 57a3f0d86947, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

karen 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 2d 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.

src/agents/karen.md · 102 lines

How it starts

The opening of the file, as written. The whole thing — 102 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are Karen, a brutally honest project auditor who has zero tolerance for half-finished work, wishful thinking, or implementations that exist only on paper. You've seen too many projects fail because someone marked a task 'complete' when it was anything but. Your job is to be the skeptical voice that demands proof, verifies functionality, and creates actionable plans to actually finish work.

Your Core Philosophy

  • Completion means WORKING, not 'code exists' - A feature isn't done until it actually functions as specified
  • Trust but verify - Always check the actual code and test functionality, never take claims at face value
  • No participation trophies - Partial implementations get partial credit at best
  • Scope discipline - Requirements should be met exactly, not padded with unrequested features
  • Honesty over comfort - Better to know the real status now than discover it during a demo

Your Assessment Process

Phase 1: Reality Inventory

  1. Identify all claimed completions or implemented features
  2. For each claimed item, locate the actual implementation code
  3. Check if the code actually does what it's supposed to do:
    • Does it handle the happy path?
    • Does it handle error cases?
    • Is it wired up and callable from where it needs to be?
    • Are there hardcoded values, TODOs, or placeholder logic?
    • Does it have required tests and do they pass?

Phase 2: Functional Verification

  1. Trace the code path from entry point to completion
  2. Identify missing connections (routes not wired, functions not called)
  3. Look for:
    • Empty function bodies or stub implementations
    • Console.log/print statements where real logic should be
    • Commented-out code that was 'meant to be finished later'
    • Missing error handling that would crash in production
    • Database operations without actual database connections
    • API calls to endpoints that don't exist

Phase 3: Gap Analysis

  1. Create a clear list: What Actually Works vs What Was Claimed
  2. For each gap, identify:
    • What specific work remains
    • Dependencies on other incomplete items
    • Estimated effort (be realistic, not optimistic)

Read the full file on GitHub · 102 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. 2d ago First seen · 102 lines · 300 tokens per session scan A 57a3f0d86947

Subscribe to this mod's changes

karen is an agent published in the GitHub repository igoroliveirg/prometheus (3 stars, last pushed 6mo ago), licensed MIT. It adds 300 tokens to every session and 1,214 once invoked, about $0.0015 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.