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 skills/closetheloops/moradin/definenpx skills add CloseTheLoops/moradin --skill definegit clone --depth 1 https://github.com/CloseTheLoops/moradinWhat 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 | $0.00062 | $0.00949 |
| Opus 5 | $0.00031 | $0.00475 |
| Sonnet 5 | $0.00012 | $0.00190 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
moradin-define 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.
How it starts
The opening of the file, as written. The whole thing — 49 lines — stays where its author put it; the contents beside it link to each section on GitHub.
moradin:define
Turn "I have an idea" into a plan someone can build from — in 10–15 minutes at light level. Roughly 43% of failed products die because nobody needed them, so this stage forces who has this problem before any feature talk.
When invoked
/moradin:define (dispatcher routes here) or directly with the idea: /moradin:define "an app that ..."
Requires .forge/profile.md (run /moradin:forge first if missing). Read profile.md and, if it exists, the current plan.md (amendment mode — supersede only the affected sections).
The one interaction rule
You draft, the operator corrects. Never ask them to produce an artifact from a blank page ("write your user stories" is banned). For every step: propose a concrete draft from what they've told you, then ask what's wrong with it. Timebox the whole conversation — say up front "this takes about 15 minutes" and honor it. Good-enough v0 answers are explicitly fine; say so when they stall.
The interview — light level (all profiles do these 6)
Work through in order. One step at a time, conversationally.
- Who + problem. Draft: "[specific person] struggles to [specific thing]." Reject "everyone" and "save time" phrasings — push for a person type they could actually name and a struggle they've actually seen. This is the step most failed products skipped.
- Job story. Draft: "When [situation], I want to [motivation], so I can [outcome]." One sentence. They edit.
- Riskiest assumption. Ask: "What has to be true for anyone to use this? What's the ONE thing v1 must prove?" Also ask: "How do you know this problem exists?" If the honest answer is "I don't" — note it; milestone 0 becomes a validation test (the measure stage will set it up).
- Walking skeleton. Ask: "Walk me through one successful use, step by step, as the user." Each step becomes a story. Cap at 7; if they list more, the extras go to the backlog.
- Appetite + the cut. Ask: "How much time before something is usable — a weekend? Two weeks?" Then go step by step: in, or not-now, against that appetite. Binary only — no maybe-tiers. Everything cut is parked in the backlog with its number, not deleted; say that out loud, it makes cutting painless.
- Premortem. Ask: "It's three weeks from now and you abandoned this. Why?" Draft one mitigation for the top answer. Milestone 1 = the skeleton works end-to-end.
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.
- 2d ago First seen · 49 lines · 62 tokens per session scan A a42efb8a2a40
moradin-define is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 24d ago), licensed MIT. It adds 62 tokens to every session and 949 once invoked, about $0.0003 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 skills, from other repositories
okf-harness-bootstrap
This unified entrypoint routes setup and workspace maintenance without making the user choose a mode.
okf-harness
One Door routes OKF Harness workspace requests to exactly one internal workflow at a time.
llm-wiki-faq
Explain LLM-Wiki adoption and answer stakeholder objections. Use when the user wants a concise FAQ response, evidence summary, ROI framing, migration answer, or plain-language rebuttal; route adversarial risk registers and bad-fit audits to llm-wiki-critique-audit.
llm-wiki-mcp-integration
Design or review MCP/API integration for an LLM-Wiki. Use when the user wants agents such as Claude Code, Codex, Cursor, ChatGPT, VS Code, GitHub Copilot, LangGraph or other MCP clients to search, read, lint, rescan, propose, review or export wiki knowledge through MCP or a local/remote API.
llm-wiki-retrieval-architect
Design the retrieval/indexing layer for an LLM-Wiki. Use for lexical/FTS search, BM25, hybrid retrieval, vector databases, rerankers, metadata filters, or GraphRAG, or when rg/index.md no longer retrieves enough context; route whole-stack local-first tooling choices to llm-wiki-local-first-stack.
llm-wiki-eval-tooling
Select evaluation tools and CI gates for LLM-Wiki measurement. Use when the user asks which eval framework, dataset format, scorecard file, red-team config, prompt regression test, hosted/self-hosted service, or human calibration workflow to use; route actual pilot runs to llm-wiki-eval.