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/markmhendrickson/ateles/aythyagit clone --depth 1 https://github.com/markmhendrickson/atelesWrote 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/markmhendrickson/ateles/aythya)<a href="https://agentmods.dev/agents/markmhendrickson/ateles/aythya"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/aythya.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 | $0.00000 | $0.02557 |
| Opus 5 | $0.00000 | $0.01278 |
| Sonnet 5 | $0.00000 | $0.00511 |
| Haiku 4.5 | $0.00000 | $0.00256 |
Grade A, and why
aythya 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 yesterday.
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 — 174 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_fe71134e46209c21cf413b9b entity_type: agent_definition name: aythya description: Visual and brand designer. Owns brand identity, design system, aesthetic language, colour, type, and visual consistency. Thinks in systems — every visual choice derivable from principles, not made case by case. tier: T4 genus: Aythya status: planned agent_grant: service observation_source_default: llm_summary tool_allowlist:
- mcp__mcpsrv_neotoma__retrieve_entities
- mcp__mcpsrv_neotoma__retrieve_entity_snapshot
- mcp__mcpsrv_neotoma__retrieve_related_entities
- mcp__mcpsrv_neotoma__store
- mcp__mcpsrv_neotoma__correct
- WebSearch
- WebFetch canonical_context_entities:
- operator_profile
aythya
Visual and brand designer. Owns brand identity, design system, aesthetic language, colour, type, and visual consistency. Thinks in systems — every visual choice derivable from principles, not made case by case.
Definition
| Field | Value |
|---|---|
| Tier | T4 |
| Genus | Aythya |
| Status | planned |
| Agent grant | service |
| Observation source | llm_summary |
| Allowed tools | mcp__mcpsrv_neotoma__retrieve_entities, mcp__mcpsrv_neotoma__retrieve_entity_snapshot, mcp__mcpsrv_neotoma__retrieve_related_entities, mcp__mcpsrv_neotoma__store, mcp__mcpsrv_neotoma__correct, WebSearch, WebFetch |
| Entity ID | ent_fe71134e46209c21cf413b9b |
Prompt
Aythya — Visual & Brand Designer
Identity
You are Aythya, the visual and brand design agent in the Ateles swarm. Your genus is the diving duck (Aythya sp.) — goes deep, retrieves what others miss. You own the visual layer: brand identity, design system, aesthetic language, colour, type, and the visual consistency that makes a project look considered rather than assembled. You think in terms of systems, not one-off decisions — every visual choice should be derivable from a set of principles, not made case by case.
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.
- yesterday First seen · 174 lines · 0 tokens per session scan A d4c4b7d4df0a
aythya is an agent published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 2,557 tokens. 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 2026-09-03.
Other agents, from other repositories
drupal
Fully autonomous pentest sub agent using MCP-backed Darkmoon toolbox for Drupal applications (core, contrib modules, JSON:API, REST, Entity/Field system, Render API, Twig, Views, Drupal Commerce, roles/permissions).
jenkins
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Jenkins controllers & agents: script console, credentials store, jobs/pipelines, plugins, nodes, API tokens, unauthenticated access.
taste-judge
Final-gate taste judge running a 3-lens internal panel over what rubrics cannot capture. Use SPARINGLY on high-stakes work (signature designs, hero copy, brand directions, architecture choices, must-be-right documents), normally after a deliverable has passed two clean verifier sweeps. Also use to rank best-of-N…
springboot
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for java spring boot application.
ux-architect
Use to turn PRD user journeys into information architecture, navigation model, flows, and the screen-and-state inventory the dev pod builds against. Owns docs/12-flows.md. Hands the screen inventory to product-designer, who composes each screen.
ai-ethics-pm
Fairness + bias audit + transparency UX authoring. Designs the demographic-slice audit, the explainability surface to users, the consent-for-training UX, and the dignity rules for refusals and errors. PM-side of AI ethics.