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/formatnpx skills add modeled-information-format/mnemonic --skill formatgit 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 | $0.00015 | $0.01268 |
| Opus 5 | $0.00008 | $0.00634 |
| Sonnet 5 | $0.00003 | $0.00254 |
| Haiku 4.5 | $0.00002 | $0.00127 |
Grade A, and why
format 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.
How it starts
The opening of the file, as written. The whole thing — 192 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 Format Skill
MIF Level 3 specification, templates, and formatting guidelines.
Trigger Phrases
- "memory format", "MIF format", "frontmatter template", "memory template", "mnemonic schema"
Quick Start: Minimal Memory
Only 4 fields are required. Everything else is optional.
---
id: 550e8400-e29b-41d4-a716-446655440000
title: "Human-readable title"
type: semantic
created: 2026-01-23T10:30:00Z
---
# Title
Content here.
That's it. Add optional fields only when you need them.
File Naming
{slug}.memory.md
- slug: URL-safe title, lowercase, max 50 chars
- UUID is stored only in the frontmatter
id:field - If a file with the same slug already exists, content is merged
Full Optional Fields Reference
---
# REQUIRED (always include these 4)
id: 550e8400-e29b-41d4-a716-446655440000
title: "Human-readable title"
type: semantic
created: 2026-01-23T10:30:00Z
# COMMON
modified: 2026-01-23T14:22:00Z
namespace: _semantic/decisions/project
tags:
- architecture
- database
# BI-TEMPORAL TRACKING
temporal:
valid_from: 2026-01-23T00:00:00Z
valid_until: null
recorded_at: 2026-01-23T10:30:00Z
ttl: P90D
decay:
model: exponential
half_life: P7D
strength: 0.85
access_count: 5
last_accessed: 2026-01-23T14:22:00Z
# PROVENANCE
provenance:
source_type: conversation # user_explicit | inferred | conversation
source_ref: file:///path/to/source.ts:42
agent: claude-opus-4
confidence: 0.95
session_id: abc123
# CODE REFERENCES
code_refs:
- file: src/auth/handler.ts
line: 42
symbol: authenticateUser
type: function # function | class | method | variable | type
# CITATIONS
citations:
- type: documentation # paper | documentation | blog | github | stackoverflow | article
title: "Source Title"
url: https://example.com/source
author: "Author Name"
date: 2026-01-23
accessed: 2026-01-23T10:30:00Z
relevance: 0.90
note: "Brief description"
# COMPRESSION (auto-generated by gc --compress)
summary: "Concise 2-3 sentence summary (max 500 chars)"
compressed_at: 2026-01-24T10:00:00Z
---
# Memory Title
Content in markdown format.
## Relationships
- relates-to [[other-memory-id]]
- supersedes [[old-memory-id]]
- derived-from [[source-memory-id]]
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 · 192 lines · 15 tokens per session scan A 6e289760cb76
format is a skill published in the GitHub repository modeled-information-format/mnemonic (22 stars, last pushed 1mo ago), licensed MIT. It adds 15 tokens to every session and 1,268 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 2026-08-30.
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.
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.
council
Multi-persona debate for founder decisions. 4 personas argue a topic across structured rounds.
linkedin-brand
LinkedIn + personal brand system for founders. Apply when drafting LinkedIn posts, reactions, DMs, LinkedIn About sections, or planning LLM visibility.