format

A formatting guide for MIF Level 3, a file format for storing structured memories in Markdown. It defines required fields, optional fields, file names, and templates.

In plain words
What is it for?
Use it to create, name, and format mnemonic memory files. It helps define memory types, namespaces, dates, tags, and other metadata.
Why use it?
It removes guesswork when creating memory files that can be found and combined consistently. It also explains which information is required and which is optional.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/modeled-information-format/mnemonic/format
Any agent
npx skills add modeled-information-format/mnemonic --skill format
Clone the repo
git clone --depth 1 https://github.com/modeled-information-format/mnemonic

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,268 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 2d ago against content hash 6e289760cb76, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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.

skills/format/SKILL.md · 192 lines

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]]

Read the full file on GitHub · 192 lines

Changes

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.

  1. 2d ago First seen · 192 lines · 15 tokens per session scan A 6e289760cb76

Subscribe to this mod's changes

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.