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/researchnpx skills add CloseTheLoops/moradin --skill researchgit clone --depth 1 https://github.com/CloseTheLoops/moradinWrote 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/skills/closetheloops/moradin/research)<a href="https://agentmods.dev/skills/closetheloops/moradin/research"><img src="https://agentmods.dev/badge/skills/closetheloops/moradin/research.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 | $0.00056 | $0.00947 |
| Opus 5 | $0.00028 | $0.00474 |
| Sonnet 5 | $0.00011 | $0.00189 |
| Haiku 4.5 | $0.00006 | $0.00095 |
Grade A, and why
moradin-research 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 — 47 lines — stays where its author put it; the contents beside it link to each section on GitHub.
moradin:research
Replace "just search and hope" with directed, verified research. The operator doesn't supply the expert prompting — it lives here. Takes minutes for cheap decisions, longer only where being wrong is expensive.
When invoked
/moradin:research — requires .forge/plan.md and .forge/measure.md (run define/measure first). Read both, plus profile.md and memory/references/forge_tool_defaults.md (if that file is >60 days old, re-verify anything you use from it).
Step 1 — Generate the questions, confirm the list
Derive the open decisions from the plan yourself (stack, hosting, data sources, auth/payments/AI services, anything the skeleton needs that doesn't exist yet). Present the list in one short message — "here's what I think needs researching, anything to add or cut?" — and wait for the nod. Don't research questions nobody asked.
Step 2 — Classify each decision by door type
- Expensive door (data model, payment provider, auth, core data dependency — costly to exit): full verification, a background agent per decision.
- Cheap door (UI library, log storage, host for a $0 experiment — an afternoon to reverse): minutes of checking, 2 options, no agent fan-out needed.
Timebox accordingly and say which is which. More research on a cheap door is procrastination.
Step 3 — Verify (the checklist every option must pass)
No claim from memory — every fact fetched today, with URL + date recorded:
- Existence: official registry/docs page fetched for every package, API, endpoint, and model ID named. (LLMs hallucinate packages; slopsquatting is a real attack.)
- Data shape: for any API whose fields will drive a threshold or decision, make one real call with a real payload and record a sample response. Existence + price ≠ semantics — this is the check that catches "$0 means pre-migration" surprises. ([[verify_data_shape_not_just_existence]])
- Pricing: vendor's live pricing page — free-tier limits, card required?, hard spend cap available?, overage behavior (throttle vs bill).
- Pricing history: repricings/tier removals/acquisitions in the last 24 months → risk line. Flag the named risk category wherever found: free tier + usage billing + no hard cap.
- Maintenance: last human commit ≤90 days, a release in 12 months, contributor concentration over the last 12 months (never lifetime, never stars).
- Adoption trend + responsiveness: download-trend direction over 12 months; median time-to-first-response on recent issues.
- Lock-in: the concrete exit path (export format, protocol, substitute) and migration effort in days — this sets the door type honestly.
- UNVERIFIED labeling: anything that resisted verification is included with the flag, never silently.
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 · 47 lines · 56 tokens per session scan A 53fc5109042c
moradin-research is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 26d ago), licensed MIT. It adds 56 tokens to every session and 947 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.