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/closenpx skills add CloseTheLoops/moradin --skill closegit 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 | $0.00055 | $0.00853 |
| Opus 5 | $0.00028 | $0.00426 |
| Sonnet 5 | $0.00011 | $0.00171 |
| Haiku 4.5 | $0.00006 | $0.00085 |
Grade A, and why
moradin-close scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
2. **Logged-out probe** — from outside the app (curl/incognito, no session): attempt to read and write every endpoint, table, and storage bucket. Expect denial everywhere. This one check would have prevented the era's wo How it starts
The opening of the file, as written. The whole thing — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
moradin:close
Every item here traces to a documented disaster that hit builders exactly like this project's operator. The profile never shrinks this list — scoping keys to release significance: first public launch or personal data involved ⇒ Extended; otherwise Core.
When invoked
/moradin:close — after a milestone ships, before ending a project phase. Reads all of .forge/.
Core (every ship, 30–60 min, agent-driven)
- Secrets — scan the entire git history, not just HEAD. Any hit: rotate the key, never just delete the line (most keys leaked years ago are still live). Confirm nothing secret sits in client-delivered code.
- Logged-out probe — from outside the app (curl/incognito, no session): attempt to read and write every endpoint, table, and storage bucket. Expect denial everywhere. This one check would have prevented the era's worst vibe-coded breaches.
- Database rules — row-level security / access rules on every table, verified with the platform's own linter where one exists.
- A way back — automatic backup on, and one real restore performed into a scratch location. An untested backup is a hope, not a backup.
- Spend caps — billing alerts + hard caps on every metered API the project touches; note any service that cannot cap as a standing risk.
- Monitoring heartbeat — error tracker receives a deliberate test error; uptime check answers.
- Production smoke test — the golden path (arrive → core action → data persists), in production, as a stranger.
- Contact route — a working way for a user to reach the operator; doubles as the data-deletion request path.
- Personal data? — if the app stores any: privacy policy + terms generated and linked, deletion route actually works.
- Closed-loop audit — every plan item and backlog entry is
doneordeferredwith a reason. Nothing dangles unlabeled. - Converge — reconcile
.forge/files against the actual code, both directions: constants the build amended go into the plan; code that drifted from a decision gets flagged (supersede or fix). - Retro, four questions — what shipped · what broke or surprised · what would we do differently · what's explicitly deferred.
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 · 39 lines · 55 tokens per session scan A e71fa40b0307
moradin-close is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 24d ago), licensed MIT. It adds 55 tokens to every session and 853 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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.