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.
git clone --depth 1 https://github.com/RDEL-Group/compound-knowledge-workWrote 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.
[](https://agentmods.dev/agents/rdel-group/compound-knowledge-work/ckw-reviewer-stress)<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.
<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>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.
| Model | Per session | Once 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 |
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.
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
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.
- 10d ago First seen · 145 lines · 41 tokens per session scan A 13377eaf725a
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.
Other agents, from other repositories
ecto-schema-designer
Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.
corporate-strategy
Corporate Strategy (CSO). Owns plugins/corporate-strategy/ and nothing else. Delegate work in this department's remit here.
demand-generation
Demand Generation (CMO). Owns plugins/demand-generation/ and nothing else. Delegate work in this department's remit here.
integrations-engineer
Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…
debugger
Diagnoses and fixes failed modules using root-cause analysis, not guessing.
ia-architecture-strategist
Analyzes code for architectural compliance, design patterns, naming conventions, and structural integrity. Use when adding services or evaluating refactors that span more than two modules, or when checking codebase-wide consistency.