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/corenpx skills add modeled-information-format/mnemonic --skill coregit clone --depth 1 https://github.com/modeled-information-format/mnemonicWhat 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 | $0.00109 | $0.01443 |
| Opus 5 | $0.00055 | $0.00722 |
| Sonnet 5 | $0.00022 | $0.00289 |
| Haiku 4.5 | $0.00011 | $0.00144 |
Grade A, and why
core 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 yesterday.
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 — 182 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 Core
Memory system operations. See references/ for full documentation.
Trigger Phrases
Capture Triggers (silently capture when user says):
Decisions (namespace: _semantic/decisions):
- "I've decided", "let's use", "we're going with"
- "we'll use", "I'm choosing", "going forward with"
- "the decision is", "we chose", "decided on"
Learnings (namespace: _semantic/knowledge):
- "I learned", "turns out", "discovered that"
- "TIL", "gotcha", "found out", "realized"
- "the root cause was", "it was because"
Patterns (namespace: _procedural/patterns):
- "always use", "never do", "when X do Y"
- "the pattern is", "we should always", "convention is"
- "standard approach", "best practice here"
Blockers (namespace: _episodic/sessions/blockers):
- "I'm stuck on", "blocked by", "can't figure out"
- "hitting a wall", "the problem is", "struggling with"
Context (namespace: _semantic/knowledge):
- "important to know", "keep in mind", "context is"
- "background", "constraint", "requirement"
Recall Triggers (search memories when user asks):
- "what did we decide about", "how do we handle"
- "what's our approach to", "check for decisions"
- "any learnings about", "patterns for"
- "remind me", "what do we know about"
- "search memories", "recall", "find memories"
Silent Capture Protocol
When to capture: Only capture when the user explicitly states a decision, learning, pattern, or blocker in their message. Do NOT capture based on Claude's own suggestions or recommendations.
When trigger phrases are detected:
- Capture to appropriate namespace WITHOUT announcing
- Do NOT say "I'm capturing this" or similar
- Continue natural conversation flow
- Memory creation is invisible to user
What ships with it
4 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- yesterday First seen · 182 lines · 109 tokens per session scan A c2aff2e1e39b
core is a skill published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 109 tokens to every session and 1,443 once invoked, about $0.0005 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
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.
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.
ori-memory
Persistent agent memory with learning retrieval. Knowledge graph on markdown files — capture insights, decisions, research, and learnings during work, then retrieve them weeks or months later. Use when knowledge is too valuable to lose but too much to inject into every prompt.
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".
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.