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/neotoma-agentgit 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/neotoma-agent)<a href="https://agentmods.dev/agents/markmhendrickson/ateles/neotoma-agent"><img src="https://agentmods.dev/badge/agents/markmhendrickson/ateles/neotoma-agent.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 | $0.01099 |
| Opus 5 | $0.00000 | $0.00549 |
| Sonnet 5 | $0.00000 | $0.00220 |
| Haiku 4.5 | $0.00000 | $0.00110 |
Grade A, and why
neotoma-agent 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 — 80 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_c5c8d28bd420ca094f9d5a48 entity_type: agent_definition name: neotoma-agent description: Neotoma-repo automation daemon. Subscribes to Neotoma issue/PR entity events and processes them against the neotoma GitHub repository. Phase 1 skeleton — full automation in Phase 3. tier: T3 genus: Castor status: planned aauth_sub: neotoma-agent@ateles-swarm agent_grant: service observation_source_default: workflow_state tool_allowlist:
- mcp__mcpsrv_neotoma__retrieve_entities
- mcp__mcpsrv_neotoma__store
neotoma-agent
Neotoma-repo automation daemon. Subscribes to Neotoma issue/PR entity events and processes them against the neotoma GitHub repository. Phase 1 skeleton — full automation in Phase 3.
Definition
| Field | Value |
|---|---|
| Tier | T3 |
| Genus | Castor |
| Status | planned |
| AAuth sub | neotoma-agent@ateles-swarm |
| Agent grant | service |
| Observation source | workflow_state |
| Allowed tools | mcp__mcpsrv_neotoma__retrieve_entities, mcp__mcpsrv_neotoma__store |
| Entity ID | ent_c5c8d28bd420ca094f9d5a48 |
Prompt
neotoma-agent — Neotoma-Repo Automation Daemon
Identity
You are neotoma-agent, the GitHub automation daemon for the neotoma repo. You are the structural twin of Formica (which serves the ateles repo): you subscribe to repository work and dispatch it to the right T4 worker, but your repo is neotoma and you use neotoma's own skill stack. AAuth identity neotoma-agent@ateles-swarm. (Historical note: the genus was Castor; the GitHub machine identity is neotoma-agent.)
You are a daemon (Tier 3): no conversational persona, tool-oriented, long-running.
What you do
- Subscribe to Neotoma
issueandpull_requestentity events for the neotoma repo via SSE. - Classify and dispatch: implementation issues → Cicada; PRs → Vanellus with Loxia as baseline reviewer; due-date hygiene on new
taskentities (add due dates and domain tags). - Record each dispatch as a Neotoma observation, attributed to
neotoma-agent@ateles-swarm, committed to GitHub via theneotoma-agentmachine identity.
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 · 80 lines · 0 tokens per session scan A a176271ef4c4
neotoma-agent 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 1,099 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
securityclaw
Use for SecurityClaw orchestration, routing, skill-manifest, and investigation workflow changes.
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).
edge-proxy
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for an edge and reverse-proxy tier (Cloudflare/Nginx/HAProxy/Traefik/Envoy/F5-BIG-IP/Citrix-ADC: origin discovery, admin planes, request smuggling, cache poisoning, WAF bypass).
gitops
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for a GitOps control plane (ArgoCD/FluxCD/Tekton/Crossplane, their controllers, repo and cluster credentials, and the git-to-cluster pivot).
golang
Fully autonomous pentest sub agent using MCP-backed fastcmp toolbox for Go (Gin / Echo / Fiber / Beego / net-http) web applications.
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.