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/initnpx skills add CloseTheLoops/moradin --skill initgit 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 | $0.00019 | $0.00494 |
| Opus 5 | $0.00010 | $0.00247 |
| Sonnet 5 | $0.00004 | $0.00099 |
| Haiku 4.5 | $0.00002 | $0.00049 |
Grade A, and why
moradin-init 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.
What it actually says
moradin:init
Use this skill to set up a fresh Moradin workshop. Typically run once per instance, right after cloning the template.
When invoked
/moradin:init
The operator just cloned the template (or used "Use this template" on GitHub). This skill walks them through first-time setup.
What you do
-
Verify structure. Check that
memory/{principles,patterns,references,lessons}/,projects/,templates/,examples/exist. If any are missing, create them. -
Initialize indexes. Run
python scripts/refresh_indexes.pyto create empty_INDEX.mdfiles. -
Ask the operator:
- "Do you have an existing project you want Moradin to help build? If yes, tell me its name and where it lives."
- "If yes, I'll create
projects/<name>/state.mdand link it."
-
Optional first content.
- "Want to capture your first principle? (universal rules that apply to any project)"
- If yes, walk through writing one to
memory/principles/usingtemplates/principle.template.md.
-
Point them at the front door. Explain in two sentences: "The main way to use Moradin is
/moradin:forge— open a session, name a project folder or a brand-new idea, and it guides you from there, start to finish. Everything else (capture, recall, audit) is the memory layer that makes each project smarter than the last." -
Summarize what's set up. List the directories, the first project slot if created, the first principle if any — and end with the
/moradin:forgepointer.
Don't
- Don't pre-fill memory with content. Moradin starts empty. The operator fills it.
- Don't write to GodTech or any other target project during init.
- Don't auto-tag the first principle without asking the operator to confirm tags.
Output
- Updated
_INDEX.mdfiles (empty initially) - Optional
projects/<name>/state.mdif operator gave a project - Optional
memory/principles/<first>.mdif operator gave a principle
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 · 45 lines · 19 tokens per session scan A 60c4c6d122a2
moradin-init is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 24d ago), licensed MIT. It adds 19 tokens to every session and 494 once invoked, about $0.0001 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.