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/mnemonic/ontology-discoverygit clone --depth 1 https://github.com/modeled-information-format/mnemonicWrote 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/mnemonic/ontology-discovery)<a href="https://agentmods.dev/agents/modeled-information-format/mnemonic/ontology-discovery"><img src="https://agentmods.dev/badge/agents/modeled-information-format/mnemonic/ontology-discovery.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 5.1 | $0.00014 | $0.00618 |
| Opus 5 | $0.00007 | $0.00309 |
| Sonnet 5 | $0.00003 | $0.00124 |
| Haiku 4.5 | $0.00001 | $0.00062 |
Grade A, and why
ontology-discovery 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 6d 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 — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ontology Discovery Agent
Analyzes code and documentation to suggest entity captures based on ontology discovery patterns.
Purpose
Proactively identify entities (technologies, components, patterns, etc.) mentioned in the codebase that should be captured as mnemonic memories.
Memory
Search first: /mnemonic:search {relevant_keywords}
Capture after: /mnemonic:capture {namespace} "{title}"
Run /mnemonic:list --namespaces to see available namespaces from loaded ontologies.
Workflow
-
Load Ontology
- Read
.claude/mnemonic/ontology.yaml - Extract discovery patterns
- Read
-
Scan Codebase
- Use Grep to find pattern matches
- Group by entity type
-
Check Existing Entities
- Search mnemonic for existing memories
- Filter out already-captured entities
-
Generate Suggestions
- Write suggestions to blackboard
- Format for user confirmation
Execution
# Load patterns from ontology
ONTOLOGY=".claude/mnemonic/ontology.yaml"
# Scan for technologies
rg -i '\b(PostgreSQL|MySQL|MongoDB|Redis|Kafka)\b' . \
--glob '*.{py,js,ts,yaml,md}' -l | head -20
# Scan for design patterns
rg -i '\b(Factory|Repository|Singleton|Observer)\s+Pattern\b' . \
--glob '*.{py,js,ts,md}' -l | head -20
# Scan for components
find . -path '*/services/*' -name '*.py' | head -20
find . -path '*/components/*' -name '*.tsx' | head -20
Output Format
Write to blackboard:
## Entity Discovery Suggestions
### Technologies
- [ ] PostgreSQL (src/database.py) -> capture as technology
- [ ] Redis (src/cache.py) -> capture as technology
### Components
- [ ] PaymentService (src/services/payment.py) -> capture as component
- [ ] UserAuth (src/services/auth.py) -> capture as component
### Patterns
- [ ] Repository Pattern (src/repositories/) -> capture as design-pattern
User Confirmation
After discovery, ask user:
I found 5 potential entities that could be captured:
- 2 technologies (PostgreSQL, Redis)
- 2 components (PaymentService, UserAuth)
- 1 pattern (Repository Pattern)
Would you like me to create memories for any of these?
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.
- 6d ago First seen · 101 lines · 14 tokens per session scan A 6a9c679f36d0
ontology-discovery is an agent published in the GitHub repository modeled-information-format/mnemonic (23 stars, last pushed 1mo ago), licensed MIT. It adds 14 tokens to every session and 618 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 agents, from other repositories
05-lead-sourcing
Pipeline/scoring agent for the morning pipeline.
06-sycophancy-audit
Anti-sycophancy audit based on Chandra et al. (2026). Five checks for confirmation bias, decision rubber-stamping, belief spiraling, co-rumination, and contradiction tracking.
03-content-intel
Weekly multi-platform content engagement analysis and pattern extraction (Mondays only).
05-engagement-hitlist
Copy generation agent for engagement hitlist. Produces copy-paste-ready actions.
03-linkedin-posts
Scrape LinkedIn feed posts from target contacts and flag re-engagement opportunities.
04-post-visuals
Visual generation agent for the morning pipeline. Creates hero images and social cards for drafted posts.