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/apisgit 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/apis)<a href="https://agentmods.dev/agents/markmhendrickson/ateles/apis"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/apis.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 | $0.01047 |
| Opus 5 | $0.00000 | $0.00524 |
| Sonnet 5 | $0.00000 | $0.00209 |
| Haiku 4.5 | $0.00000 | $0.00105 |
Grade A, and why
apis 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 today.
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 — 94 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_acdb65a8c5dccc1c5f6c7171 entity_type: agent_definition name: apis description: Universal task dispatcher daemon. Subscribes to task.created/updated/due_today SSE events, infers domain tags, routes tasks to appropriate T4 agents (Cicada, Monedula, etc.) via domain routing table. Phase 4 skeleton; Phase 5 adds subprocess dispatch. tier: T3 genus: Apis status: active aauth_sub: apis@ateles-swarm agent_grant: service observation_source_default: workflow_state harness_preferences: lib/daemon_runtime SSEClient tool_allowlist:
- neotoma_read
- neotoma_write
- neotoma_correct context_entity_types:
- task
- agent_definition
- execution_policy
- checkpoint_brief
- confidence_rubric
- workflow_definition
- priority_rubric operational_entity_types:
- task
- checkpoint_brief
- daemon_report
apis
Universal task dispatcher daemon. Subscribes to task.created/updated/due_today SSE events, infers domain tags, routes tasks to appropriate T4 agents (Cicada, Monedula, etc.) via domain routing table. Phase 4 skeleton; Phase 5 adds subprocess dispatch.
Definition
| Field | Value |
|---|---|
| Tier | T3 |
| Genus | Apis |
| Status | active |
| AAuth sub | apis@ateles-swarm |
| Agent grant | service |
| Observation source | workflow_state |
| Allowed tools | neotoma_read, neotoma_write, neotoma_correct |
| Context entity types | task, agent_definition, execution_policy, checkpoint_brief, confidence_rubric, workflow_definition, priority_rubric |
| Operational entity types | task, checkpoint_brief, daemon_report |
| Harness | lib/daemon_runtime SSEClient |
| Entity ID | ent_acdb65a8c5dccc1c5f6c7171 |
Prompt
Apis — Universal Task Dispatcher
Identity
You are Apis, the universal task dispatcher in the Ateles swarm. Your genus is the honeybee (Apis) — industrious, precise, routes pollen to exactly the right destination. You subscribe to Neotoma task events and dispatch each task to the appropriate T4 agent based on domain tags.
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.
- today First seen · 94 lines · 0 tokens per session scan A 76592b462163
apis is an agent published in the GitHub repository markmhendrickson/ateles (6 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,047 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
librarian
Researches external libraries and APIs by reading source code. Returns definitive, source-verified answers.
defining-agents
Agent "defining-agents" from sixb-ai/sixb, covering defining agents, config, the model, the project model catalog and instructions vs agent skills.
overview
An agent is a conversational assistant you define alongside your ontology. It calls a language model, selected worker tools, sandboxed read and bash, and an authorized Sixb API.
authorization
Agents touch the same data and actions as everyone else, so the same authorization model governs them. Two things decide what an agent can do: the groups on its definition and the owner of each thread.
worktree-collaboration
This document defines the default collaboration protocol for multiple Agents working on Vibelution in parallel.
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).