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/modeled-information-format/mnemonic/searchnpx skills add modeled-information-format/mnemonic --skill searchgit clone --depth 1 https://github.com/modeled-information-format/mnemonicWrote 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/modeled-information-format/mnemonic/search)<a href="https://agentmods.dev/skills/modeled-information-format/mnemonic/search"><img src="https://agentmods.dev/badge/skills/modeled-information-format/mnemonic/search.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 | $0.00060 | $0.01084 |
| Opus 5 | $0.00030 | $0.00542 |
| Sonnet 5 | $0.00012 | $0.00217 |
| Haiku 4.5 | $0.00006 | $0.00108 |
Grade A, and why
search 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 — 168 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
Mnemonic Search Skill
Search and filtering for mnemonic memories.
Trigger Phrases
- "search memories", "find in memories", "grep memories", "search mnemonic"
- "deep search memories", "comprehensive memory search", "synthesize knowledge about"
Core Search Patterns
By Namespace
rg "^namespace: _semantic/decisions" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
By Tag
# Single tag
rg -l "^ - architecture" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
# Multiple tags (AND)
rg -l "^ - architecture" ${MNEMONIC_ROOT}/ --glob "*.memory.md" | xargs rg -l "^ - database"
By Type
rg "^type: semantic" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "^type: episodic" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
rg "^type: procedural" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
By Date
rg "^created: 2026-01" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
By Title
rg -i '^title: ".*auth.*"' ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
By Confidence
rg "confidence: 0\.9" ${MNEMONIC_ROOT}/ --glob "*.memory.md" -l
Full-Text
rg -i "search term" ${MNEMONIC_ROOT}/ --glob "*.memory.md"
Combined: Namespace + Text
rg "database" ${MNEMONIC_ROOT} --path "*/_semantic/decisions/" --glob "*.memory.md"
Recent Files
find ${MNEMONIC_ROOT} -name "*.memory.md" -mtime -7
Progressive Disclosure Protocol
Always start at Level 1. Expand only if needed.
| Level | What | How |
|---|---|---|
| 1 (start here) | Titles only | rg -l "pattern" ${MNEMONIC_ROOT}/ --glob "*.memory.md" then extract ^title: |
| 2 | Frontmatter + summary | Read first ~50 lines of matched files |
| 3 | Full detail | Read entire memory file |
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 · 168 lines · 60 tokens per session scan A 1acd50d8a86f
search is a skill published in the GitHub repository modeled-information-format/mnemonic (23 stars, last pushed 1mo ago), licensed MIT. It adds 60 tokens to every session and 1,084 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 2026-08-30.
Other skills, from other repositories
reflect
Deep reflection skill - read memory and context, decide whether there is something worth sending.
forgetful-remember
Remember knowledge worth keeping — a decision made, a solution found, a preference stated, a pattern confirmed. Use when work surfaces something future sessions will need, or the user asks to remember something. Routes content to the right store (memory, document, code artifact, entity, procedure, file) and enforces…
audhd-executive-function
AUDHD executive function accommodations. Apply to all output the founder will act on.
learn-from-correction
Propose a principle edit to a skill or persona file based on a (agentoutput, humanoutput) correction pair. Outputs a proposal markdown for human review - never auto-edits the target file.
deck-ai
Generate modern presentation decks (PDF) from markdown content. Local open-source alternative to Gamma — uses Slidev for layouts and Unsplash for imagery. Invoke when the user asks to "make a deck", "build slides from this", or "turn this into a presentation".
research-mode
Anti-hallucination research mode. Toggle on to enforce citation requirements, source grounding, and "I don't know" behavior. Toggle off for creative work.