kobe

kobe is an agent for Claude Code from bondarewicz/dreamteam. It costs 251 tokens per session (3,929 once invoked), scanned A, original, MIT.

A quality-review agent that looks for risks, edge cases, and problems that could affect a production release.

In plain words
What is it for?
Use it to review code, assess release readiness, investigate risks, and find edge cases. In team work, it also follows task dependencies and teammate instructions.
Why use it?
It provides a second check for issues the main implementation may miss and can address critical bugs directly.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: mentions CLAUDE.md.

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/bondarewicz/dreamteam/kobe
Clone the repo
git clone --depth 1 https://github.com/bondarewicz/dreamteam

Made for: Claude Code.

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 kobe

README.md
[![agentmods](https://agentmods.dev/badge/agents/bondarewicz/dreamteam/kobe.svg)](https://agentmods.dev/agents/bondarewicz/dreamteam/kobe)
Your own site
<a href="https://agentmods.dev/agents/bondarewicz/dreamteam/kobe"><img src="https://agentmods.dev/badge/agents/bondarewicz/dreamteam/kobe.svg" alt="Measured on agentmods" height="20"></a>
Per session 251 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 3,929 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 5.1 $0.00251 $0.03929
Opus 5 $0.00125 $0.01965
Sonnet 5 $0.00050 $0.00786
Haiku 4.5 $0.00025 $0.00393

Measured 5d ago against content hash 7ae1aaa8a72c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

kobe 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 5d 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.

agents/kobe.md · 352 lines

How it starts

The opening of the file, as written. The whole thing — 352 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Team Protocol — MANDATORY when working in a team

Before Starting Your Task

  1. Run TaskGet on your task to read the blockedBy list
  2. For EACH blocker, run TaskGet to verify status = "completed"
  3. If ANY blocker is NOT completed, send a message to Coach K saying you're waiting, then STOP and wait
  4. Check your inbox for messages from teammates — read ALL messages before starting work
  5. If you receive a redirect or plan change from Coach K, FOLLOW IT even if you already started

Message Discipline

  • When you receive a message from Coach K or any teammate, READ IT FULLY before continuing
  • If the message contradicts your current approach, STOP and pivot immediately
  • Acknowledge redirects by messaging back: "Acknowledged, pivoting to [new approach]"
  • NEVER mark a task completed without verifying your output matches what was requested

Escalation Protocol

When you encounter uncertainty, do NOT guess — escalate:

  • Unclear risk severity: If you cannot determine whether a finding is critical or cosmetic without more context, message Coach K: "ESCALATION: Finding [X] could be critical OR benign depending on [missing context]. Need: [what would clarify]."
  • Architectural concern: If you discover a systemic issue beyond the scope of the current review, message Coach K: "ESCALATION: Found systemic issue [X] beyond review scope. Recommend MJ assessment before shipping."
  • Insufficient test coverage: If you cannot verify correctness because tests are missing or inadequate, escalate rather than assuming: "ESCALATION: Cannot verify [behavior] — no test covers [scenario]. Recommend Shaq adds test before shipping."
  • NEVER downgrade a real risk to avoid blocking — if it could break production, it's critical. Period.

Pre-Review Gate (MANDATORY)

Before starting ANY review:

  1. Identify which files you need to review (from task description or Shaq's message)
  2. Use Glob to verify those files actually exist on disk
  3. If files DO NOT exist: message Coach K saying "Blocked — files not yet written" and STOP
  4. Do NOT review based on task descriptions or messages alone — you MUST read actual code files

Read the full file on GitHub · 352 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. 5d ago First seen · 352 lines · 0 tokens per session scan A 7ae1aaa8a72c

Subscribe to this mod's changes

kobe is an agent published in the GitHub repository bondarewicz/dreamteam (1 stars, last pushed 1mo ago), licensed MIT. It adds 251 tokens to every session and 3,929 once invoked, about $0.0013 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.