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 agents/modeled-information-format/mif/ontology-managergit clone --depth 1 https://github.com/modeled-information-format/MIFWrote 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/agents/modeled-information-format/mif/ontology-manager)<a href="https://agentmods.dev/agents/modeled-information-format/mif/ontology-manager"><img src="https://agentmods.dev/badge/agents/modeled-information-format/mif/ontology-manager.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 | $0.00035 | $0.00997 |
| Opus 5 | $0.00017 | $0.00498 |
| Sonnet 5 | $0.00007 | $0.00199 |
| Haiku 4.5 | $0.00003 | $0.00100 |
Grade A, and why
ontology-manager 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 — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MIF Ontology Manager
Manage MIF ontology definition files. All operations are validated
against schema/ontology/ontology.schema.json.
Prerequisites
Ensure yq and jq are available. For JSON Schema validation,
python3 with jsonschema is preferred.
Available Scripts
Scripts are located at .claude/skills/ontology-manager/scripts/.
Create a New Ontology
Every ontology, base and domain, is authored in the
modeled-information-format/ontologies repo, not here — run this from a
checkout of that repo, writing into its ontologies/ directory:
bash <path-to-MIF-checkout>/.claude/skills/ontology-manager/scripts/scaffold_ontology.sh \
<id> <version> [--extends mif-base,shared-traits] \
> ontologies/<id>.ontology.yaml
id: lowercase, hyphens only (e.g.my-domain)version: semver (e.g.0.1.0)--extends: comma-separated parent ontology IDs
Validate an Ontology
bash .claude/skills/ontology-manager/scripts/validate_ontology.sh \
<file.yaml> [schema/ontology/ontology.schema.json]
Checks: YAML syntax, required fields, ID format, semver, base types, entity names, trait references, discovery regex, JSON Schema compliance.
Inspect an Ontology
bash .claude/skills/ontology-manager/scripts/inspect_ontology.sh \
<file.yaml> [--section entities|namespaces|traits|relationships|discovery] [--json]
Convert Between Formats
bash .claude/skills/ontology-manager/scripts/convert_format.sh \
<yaml2json|json2yaml|yaml2jsonld> <input> [output]
Ontology Structure
Every .ontology.yaml file has this structure:
ontology:
id: my-domain # REQUIRED: ^[a-z][a-z0-9-]*$
version: "0.1.0" # REQUIRED: semver
description: "..."
schema_url: https://mif-spec.dev/schema/ontology/ontology.schema.json
extends: [mif-base] # optional parent ontologies
namespaces: # cognitive triad hierarchy
_semantic: # facts, concepts, relationships
_episodic: # events, experiences, timelines
_procedural: # step-by-step processes
entity_types: # array of entity definitions
- name: my-entity # ^[a-z][a-z0-9-]*$
base: semantic # semantic|episodic|procedural
traits: [timestamped]
schema:
required: [name]
properties:
name: {type: string}
traits: # reusable mixins
my-trait:
fields:
my_field: {type: string}
relationships: # typed connections
my-rel:
from: [entity-a]
to: [entity-b]
symmetric: false
discovery: # auto-detection patterns
enabled: true
confidence_threshold: 0.8
content_patterns:
- pattern: "\\bkeyword\\b"
namespace: _semantic/knowledge
file_patterns:
- pattern: "auth|login"
namespaces: [_semantic/knowledge]
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 · 133 lines · 35 tokens per session scan A a24830f3f842
ontology-manager is an agent published in the GitHub repository modeled-information-format/MIF (12 stars, last pushed 2d ago), licensed MIT. It adds 35 tokens to every session and 997 once invoked, about $0.0002 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 agents, from other repositories
gke-cluster-runner
Launch a single TPU training workload on a GKE cluster via XPK, poll until completion or hang, capture xprof + HLO dumps to GCS, and report structured verdict signals back to the master agent. Stateless one-shot worker — does NOT write wiki pages, decide experiment verdicts, or update the model page. Use for every…
engram:memory-review
Review and curate memory suggestions from Engram's review queue.
markdown-accessibility-specialist
Use this agent when you need to audit and improve the accessibility of existing markdown documentation, including README files, tutorials, guides, and any .md content. This agent applies GitHub's five accessibility best practices (descriptive links, alt text, heading hierarchy, plain language, list structure) and…
Azure Principal Architect mode instructions
Provide expert Azure Principal Architect guidance using Azure Well-Architected Framework principles and Microsoft best practices.
007-knowledge-graph-integration
Integrate context hierarchy with Plan 0042's knowledge graph.
azure-architect
Expert Azure architecture guidance grounded in the Well-Architected Framework and current Microsoft docs. Use for designing new Azure solutions, reviewing existing architectures, service-selection trade-offs across reliability/security/cost/performance/operations, and multi-region or zero-trust topologies.