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/orneryd/mimir/claudette-regexgit clone --depth 1 https://github.com/orneryd/MimirWrote 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/orneryd/mimir/claudette-regex)<a href="https://agentmods.dev/agents/orneryd/mimir/claudette-regex"><img src="https://agentmods.dev/badge/agents/orneryd/mimir/claudette-regex.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 | $0.00011 | $0.06720 |
| Opus 5 | $0.00005 | $0.03360 |
| Sonnet 5 | $0.00002 | $0.01344 |
| Haiku 4.5 | $0.00001 | $0.00672 |
Grade A, and why
claudette-regex 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 5d 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.
The source is not reproduced here
A licence we could not identify
The repository carries a LICENSE file, but it is custom or dual enough that GitHub cannot name it and neither can this catalogue. Unknown terms are not permission, so the body is not copied here. Read the licence at the source and decide for yourself.
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.
- 5d ago First seen · 739 lines · 11 tokens per session scan A cc9ace0a85e0
claudette-regex is an agent published in the GitHub repository orneryd/Mimir (283 stars, last pushed 8mo ago), with no licence file. It adds 11 tokens to every session and 6,720 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
backend-engineer
Implements backend features - entities, services, controllers, validators, tests, migrations. Use for .NET implementation work that stays within src/backend/.
spring-boot-engineer
Use this agent when building enterprise Spring Boot 3+ applications requiring microservices architecture, cloud-native deployment, or reactive programming patterns.
agentic-python-specialist
Use for isolated work in agenticai/, including multi-agent orchestration, MCP client changes, configuration flow, and Python deployment wrappers.
4-refactorer
You are an expert code reviewer and refactoring specialist for Aam Digital (ndb-core). You analyze Angular/TypeScript code for quality, adherence to project conventions, and opportunities for improvement.
missing_docs_inventory.mn
Agent "missing_docs_inventory.mn" from hyperledger-iroha/iroha, covering баримт бичгийн тооллого дутуу байна and оруулгууд.
refactoring-agent
Orchestrates incremental refactoring of Rails codebases toward 37signals patterns. WHEN: Refactoring service objects to model methods, converting booleans to state records, migrating from Devise/RSpec/Sidekiq, extracting concerns, or reducing controller complexity. WHEN NOT: Building new features (use…