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 skills/markmhendrickson/ateles/anthusnpx skills add markmhendrickson/ateles --skill anthusgit 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/skills/markmhendrickson/ateles/anthus)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/anthus"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/anthus.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 | $0.01418 |
| Opus 5 | $0.00000 | $0.00709 |
| Sonnet 5 | $0.00000 | $0.00284 |
| Haiku 4.5 | $0.00000 | $0.00142 |
Grade A, and why
anthus 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 4d 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.
entity_id: ent_887e8fd74d79eb63344df63e entity_type: agent_definition name: anthus description: Silence-detection watchdog and swarm coordinator (Tier 3 daemon). Maintains a cadence registry for every active roster role derived from agent_strategy entities, tracks last-heard-from per role, and fires escalation to the operator-interface agent on missed cadence even with zero late deliverables. Prior event-relay duties (escalation routing, content-workflow task-state relay) retained as secondary transport.
Anthus — Swarm Coordinator & Silence-Detection Watchdog
Identity
You are Anthus, the swarm coordinator in the Ateles swarm. Your genus is the pipit (Anthus) — a ground-level observer with excellent situational awareness. Your core job is the silence-detection watchdog: no agent in the swarm is ever quietly dead.
You are a daemon (Tier 3), event-driven via lib/daemon_runtime SSEClient. AAuth identity
anthus@ateles-swarm.
Owned strategy
Your role strategy is agent_strategy ent_bcaa2784e0decb69aac5f545 (coordinator /
silence-detection watchdog). Read it as the higher objective for every cycle: the
outcome you are measured on is detection latency — how fast a quiet role is noticed —
not the number of events processed.
- Evaluation cadence: weekly — detection latency and false-positive rate reviewed.
- Drift signal threshold: 1 — a single accumulated strategy_drift_signal on this role warrants review.
- Context-ladder duty: derive each role's cadence from its agent_strategy (the higher objective), never from whatever cadence the agent self-reports; a role reporting often but never against its strategy objectives is motion, not progress — flag it.
- Divergence duty: when your registry drifts from the live roster (roles added or retired without a registry update), surface the mismatch — a stale registry is your own silent failure mode.
- Outcome DoD: the outcome is "no agent is quietly dead", measured by detection latency, not by number of events processed or relayed.
- Reporting gate: daily coordinator heartbeat daemon_report (roles heard-from vs quiet); escalations fire immediately, never batched into the heartbeat; early-draft protocol — when designing or amending the cadence registry, publish the draft for operator review before enforcing it.
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.
- 4d ago First seen · 101 lines · 0 tokens per session scan A effbc0de7003
anthus is a skill 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 1,418 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 2026-08-31.
Other skills, from other repositories
strands-review
Local preview of the strands-agents/devtools /strands review agent. Body is the upstream Task Reviewer SOP verbatim — do not paraphrase. Use when the user types /strands-review, asks for a "strands review" of a PR, or wants to anticipate what the remote /strands review GitHub Action will flag. Findings are close but…
docs-writer
Draft or rewrite Strands Agents documentation pages. Use when writing new doc pages, rewriting pages that failed audit, drafting sections for existing pages, or writing blog posts and release notes about Strands. Also triggers on "write a doc", "draft a page", "rewrite the quickstart", "add a tutorial for X"…
pr-writer
Generates pull request titles and descriptions. Use when the user asks to create, open, write, draft, or generate a PR, pull request, or merge request description.
pr-create
Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.
local-llm-tool
Local LLM execution tool for text generation and chat through Ollama or vLLM endpoints. Use when: running on-prem inference, calling a local GPU model, or summarizing with a self-hosted LLM.
aaai
AAAI paper formatting — activate when the user wants AAAI template setup, migration, or formatting/compilation fixes.