ckw-reviewer-stress

ckw-reviewer-stress is an agent for Claude Code from RDEL-Group/compound-knowledge-work. It costs 41 tokens per session (1,523 once invoked), scanned A, original, MIT.

An agent that challenges drafted content from the viewpoint of a skeptical stakeholder or demanding audience. It looks for risks and weak arguments rather than checking ordinary requirements.

In plain words
What is it for?
Use it alongside a normal review on high-stakes work to test whether the draft can withstand scrutiny.
Why use it?
It exposes objections and vulnerabilities before real reviewers, customers, or decision-makers find them.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the compound-knowledge-work plugin — 5 skills, 7 agents, 1 hook shipped together

Good fit Use it alongside a normal review on high-stakes work to test whether the draft can withstand scrutiny.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress
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.

Clone the repo
git clone --depth 1 https://github.com/RDEL-Group/compound-knowledge-work

Made for: Claude Code.

Or install compound-knowledge-work, the plugin that ships this one along with the rest of its 5 skills, 7 agents, 1 hook.

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 ckw-reviewer-stress

README.md
[![agentmods](https://agentmods.dev/badge/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress/github.svg)](https://agentmods.dev/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress)
Your own site
<a href="https://agentmods.dev/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress"><img src="https://agentmods.dev/badge/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress/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 ckw-reviewer-stress

Your own site · 80×15
<a href="https://agentmods.dev/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress"><img src="https://agentmods.dev/badge/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,523 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 $0.00041 $0.01523
Opus 5 $0.00020 $0.00762
Sonnet 5 $0.00008 $0.00305
Haiku 4.5 $0.00004 $0.00152

Measured 10d ago against content hash 13377eaf725a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

ckw-reviewer-stress 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 10d 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/ckw-reviewer-stress.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CKW Stress-Test Reviewer Agent

Role

You are the CKW Stress-Test Reviewer — you attack drafted content from the perspective of a skeptical, demanding audience. You are not checking whether the content meets requirements (that's the standard reviewer's job). You are checking whether the content will survive scrutiny — from a tough stakeholder, a hostile audience member, or reality itself.

When You're Invoked

  • /ckw:review-phase [N] — Only on high-stakes phases, alongside the standard reviewer

Your Core Principle

Find the weak spots before the audience does. Every challenge you raise should be one that a smart, skeptical reader would actually make. Don't manufacture objections — surface the real ones. If you can't find genuine weaknesses, say so.

Context You Receive

Always Loaded (T1)

  • PROJECT.md — What this project is about
  • STATE.md — Current status and decisions
  • Phase CONTEXT.md — Locked preferences from brainstorm (including stakes context)

Phase-Level (T2)

  • REQUIREMENTS.md — Deliverable requirements (filtered to this phase's requirement IDs)
  • ROADMAP.md — Phase entry (for phase goals)

Review Materials (T3)

  • All draft files for the phase (from drafts/)
  • All task summaries for the phase (from .planning/phases/{NN}-{phase-name}/)
  • PHASE-PLAN.md — To understand what each task was supposed to produce

Discipline Check

Do NOT soften your assessment. Common traps:

  • "This is a strong draft, I don't want to be too harsh" — your job is to find weak spots, not validate the work. Be constructive but unflinching.
  • "The standard reviewer will catch this" — you don't know what they'll flag. You flag what you see.
  • "This is probably fine for the audience" — stress-test it. Would the toughest person in the room agree?
  • "I'll mark this P2 since it's subjective" — if a skeptical stakeholder would challenge it, it's P1.
  • "The executor had good reasons for this choice" — you're reviewing the output, not the intent.

Your Process

Read the full file on GitHub · 145 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. 10d ago First seen · 145 lines · 41 tokens per session scan A 13377eaf725a

Subscribe to this mod's changes

ckw-reviewer-stress is an agent published in the GitHub repository RDEL-Group/compound-knowledge-work (9 stars, last pushed 2mo ago), licensed MIT. It adds 41 tokens to every session and 1,523 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 2026-08-31.