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/recallnpx skills add CloseTheLoops/moradin --skill recallgit 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/recall)<a href="https://agentmods.dev/skills/closetheloops/moradin/recall"><img src="https://agentmods.dev/badge/skills/closetheloops/moradin/recall.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 | $0.00018 | $0.00479 |
| Opus 5 | $0.00009 | $0.00239 |
| Sonnet 5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
moradin-recall 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 5d 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:recall
Search Moradin's memory and answer a question with citations.
When invoked
/moradin:recall <question>
or /moradin:recall <question> --topic <tag> for topic-filtered search.
What you do
-
Tokenize the question. Identify key terms.
-
Run BM25 search:
python scripts/search.py "<question>" [--topic <tag>] [--applies-to <tag>] --limit 10 -
Read the top results (typically 5-10 files). For each, read both frontmatter and body.
-
Synthesize an answer that:
- Directly addresses the question
- Cites EACH source file by path (e.g.
memory/patterns/closed_loop_eval.md) - Distinguishes between principles (universal rules), patterns (designs), references (external knowledge), and lessons (incident-derived)
- Honest about gaps: if memory doesn't have the answer, say so
-
Optional: file the synthesis back. If the synthesis itself is valuable, ask the operator: "This synthesis is valuable — file it back as a new pattern or lesson?"
Citation format
Always cite specific files. Don't say "your memory has principles about closed loops" — say "see memory/principles/close_every_loop.md."
Topic filter
If the operator's question is clearly within one topic (e.g. "what do I know about evals?"), use --topic eval to focus the search.
If unsure: search without filter first; let BM25 surface relevant docs.
Don't
- Don't synthesize without reading the actual files. Search results give you hits — read them before answering.
- Don't make up content. If the memory doesn't say it, say "memory doesn't cover this."
- Don't filter results silently. If you skip a hit, explain why.
Output
- A synthesized answer with file-path citations
- Optionally: a new file in
memory/patterns/ormemory/lessons/if the synthesis is filed back
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.
- 5d ago First seen · 55 lines · 18 tokens per session scan A 130fec2074fd
moradin-recall is a skill published in the GitHub repository CloseTheLoops/moradin (2 stars, last pushed 26d ago), licensed MIT. It adds 18 tokens to every session and 479 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
context-manager
Use when a long-running agent task needs context budgeting, checkpointing, compaction, retrieval, or capability-based model routing.
knowledge-ops
Use when an Obsidian knowledge system needs classification, deduplication, retrieval, synchronization, debt queues, or governed Agent/Wiki promotion.
session-learn
Use when a completed work session should yield durable concepts, corrections, decisions, reusable patterns, and a traceable next action.
log-session
Append a structured entry to the project's session log (docs/LOGS.md): what was done this session, files touched, decisions taken, and the next step — so the next session (or another person) can pick up the thread without re-reading git history. Run it before /clear, before closing Claude Code, or at any natural…
context-engineering
Workflow for context packets, context audits, compaction, handoffs, session memory, and deciding what AI-agent context to load, retrieve, trim, summarize, refresh, or omit. Use for context rot, context flooding, stale or missing context, task switching, and long-running agent sessions. Do not use when prompt wording…
wiki-ingest
Read a source (file, URL, or pasted text), extract the entities and concepts that matter, and file them as wiki pages with cross-references. Updates the wiki's catalog.md, journal.md, and hot.md so future sessions can find what was ingested. Use this skill whenever the user says "ingest this", "add this to the wiki"…