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 instructions/modeled-information-format/mif/copilot-instructionsgit clone --depth 1 https://github.com/modeled-information-format/MIFWhat 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 | $0.00418 | $0.00418 |
| Opus 5 | $0.00209 | $0.00209 |
| Sonnet 5 | $0.00084 | $0.00084 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
MIF copilot-instructions.md 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.
What it actually says
MIF Project - Copilot Instructions
About This Project
MIF (Modeled Information Format) is an open standard for portable AI memory representation with dual formats: Markdown and JSON-LD.
Ontology Management
This project includes an ontology system for organizing memories.
When working with ontology files (.ontology.yaml):
- Use the ontology manager agent:
.github/agents/ontology-manager.agent.md - Scripts:
.claude/skills/ontology-manager/scripts/ - Schema:
schema/ontology/ontology.schema.json
Quick Commands
# Validate an ontology
bash .claude/skills/ontology-manager/scripts/validate_ontology.sh <file.yaml>
# Scaffold a new ontology
bash .claude/skills/ontology-manager/scripts/scaffold_ontology.sh <id> <ver> > out.yaml
# Inspect ontology contents
bash .claude/skills/ontology-manager/scripts/inspect_ontology.sh <file.yaml>
# Convert formats
bash .claude/skills/ontology-manager/scripts/convert_format.sh yaml2json <in.yaml>
Key Conventions
- Ontology IDs: lowercase with hyphens (
my-domain) - Entity names: lowercase with hyphens (
support-ticket) - Base types:
semantic,episodic,procedural - Namespaces follow the cognitive triad:
_semantic/,_episodic/,_procedural/ - Version strings: semver (
0.1.0) - All ontologies should typically extend
mif-base
Project Structure
schema/ # JSON Schema definitions
ontology/ # Ontology validation schema
ontologies/ # Ontology definition files
mif-base.ontology.yaml # Base cognitive triad
shared-traits.ontology.yaml
examples/ # Domain-specific examples
scripts/ # Utility scripts
yaml2jsonld.py # YAML to JSON-LD converter
examples/ # MIF memory examples
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 · 55 lines · 418 tokens per session scan A e1698597387e
MIF copilot-instructions.md is an instructions file published in the GitHub repository modeled-information-format/MIF (12 stars, last pushed 21d ago), licensed MIT. It adds 418 tokens to every session, about $0.0021 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 instructions, from other repositories
cognee AGENTS.md
AGENTS.md instructions for topoteretes/cognee, covering repository guidelines, project structure & module organization, build, test, and development commands, runtime flags worth knowing and multi-tenancy support by backend.
hindsight CLAUDE.md
Instructions for vectorize-io/hindsight, covering claude.md, project overview, development commands, local development (api + ui) and start both api server and control plane ui.
hindsight AGENTS.md
Instructions for vectorize-io/hindsight: See CLAUDE.md for project documentation and coding conventions.
Ix CLAUDE.md
Instructions for ix-infrastructure/Ix, covering project: ix (this repo), layout, commands, cli dev (from ix-cli/) and skill + tooling (from repo root).
mulch CLAUDE.md
Instructions for jayminwest/mulch, covering claude.md, build & test commands, architecture, storage model and record types & classifications.
kipi-system AGENTS.md
AGENTS.md instructions for assafkip/kipi-system, covering q entrepreneur os, project structure, conventions, commands and build and test.