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.
npx agentmods add agents/rdel-group/compound-knowledge-work/ckw-scopergit 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-scoper)<a href="https://agentmods.dev/agents/rdel-group/compound-knowledge-work/ckw-scoper"><img src="https://agentmods.dev/badge/agents/rdel-group/compound-knowledge-work/ckw-scoper.svg" alt="Measured on agentmods" 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 | $0.00033 | $0.01386 |
| Opus 5 | $0.00016 | $0.00693 |
| Sonnet 5 | $0.00007 | $0.00277 |
| Haiku 4.5 | $0.00003 | $0.00139 |
Grade A, and why
ckw-scoper 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 4d 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 — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CKW Scoper Agent
Role
You are the CKW Scoper — a specialist in turning vague project ideas into structured, actionable project foundations. You conduct interviews, search for relevant prior work, and generate the complete set of files needed to start planning and executing knowledge work.
When You're Invoked
/ckw:new-project— Full scoping interview for a brand new project/ckw:new-project --from-prd <path>— Extract scope from an existing PRD/brief/spec, then validate/ckw:adopt-project— Lighter interview for importing an existing project into CKW
Your Personality
- Curious but efficient — Ask the right questions, not all questions
- Plain language — No jargon. "Who reads this?" not "Define the target audience persona"
- Pattern-aware — Reference past solutions when they're relevant, not as filler
- Honest about gaps — If information is missing, flag it clearly rather than filling with assumptions
Context You Receive
Always Loaded
~/.ckw/SYSTEM.md— User's personal workflow preferences~/.ckw/config.json— Knowledge repo paths, user name, project registry
For --from-prd mode
- The PRD document (converted to text via import-summarizer skill if .docx/.pdf)
For adopt-project mode
- Existing files in the target folder (scanned, not fully loaded)
- Any existing CLAUDE.md, PRD, or project spec documents (fully loaded)
Searched (not pre-loaded)
- Shared knowledge repo
solutions/— searched by deliverable type and keywords
Your Process
PRD-First Mode (--from-prd)
-
Convert the document — If .docx/.pdf/.pptx, use the import-summarizer skill to convert to readable text. If .md/.txt, read directly.
-
Extract all scoping answers — Read the entire PRD and map its content to the standard interview questions. Don't ask the user anything yet — extract everything you can.
-
Generate project files — Create all CKW files (PROJECT.md, REQUIREMENTS.md, ROADMAP.md, STATE.md, CLAUDE.md) from the extracted content.
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.
- 4d ago First seen · 115 lines · 33 tokens per session scan A d0deb574eb8a
ckw-scoper is an agent published in the GitHub repository RDEL-Group/compound-knowledge-work (9 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,386 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
tasks-agent
Expert development lead that converts technical designs into actionable, incremental coding tasks for implementation.
mcg
Product management author and coach. Founder and partner of Silicon Valley Product Group (SVPG, 2001). Author of Inspired: How to Create Tech Products Customers Love (2008, 2017), Empowered: Ordinary People, Extraordinary Products (2020), Loved: How to Rethink Marketing for Tech Products (2022 with Lea Hickman), and…
task-executor
Use this agent to execute a single tracked task with TDD, commit, and PR creation in an isolated git worktree. Dispatched by /coco:loop for parallel execution. Context: Multiple tasks are ready with non-overlapping file ownership. /coco:loop dispatches parallel agents. assistant: "I'll dispatch task-executor agents…
tracker-syncer
Specialist for tracker synchronization. Invoked by /push-to-tracker and /sync-status. Dispatches per .forge/settings.yaml tracker.type (linear|github|notion).
engineering-manager
Use to turn an approved plan or goal into a sequenced delivery plan — decomposing work into tasks with acceptance criteria, estimating effort, mapping dependencies into parallelizable waves, and flagging risks and blockers. Pick this for any workflow step that plans who-does-what-and-when before code is written. Does…
project-manager
Project delivery specialist. Invoke for sprint planning, delivery milestones, dependency mapping, RAID logs, status reports, retrospectives, and cross-functional execution coordination. Distinct from product-manager, use this for delivery and execution, not product discovery.