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/waxwingnpx skills add markmhendrickson/ateles --skill waxwinggit 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/waxwing)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/waxwing"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/waxwing.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 | $0.05267 |
| Opus 5 | $0.00000 | $0.02634 |
| Sonnet 5 | $0.00000 | $0.01053 |
| Haiku 4.5 | $0.00000 | $0.00527 |
Grade A, and why
waxwing 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 — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_3425a79b4c39f08cdb0c62f8 entity_type: agent_definition name: waxwing description: Invoke Waxwing (formerly Bombycilla; renamed 2026-06-12 for voice/ASR robustness), the technical architect agent — architecture reviews, schema design, interface contracts, and ADRs grounded in Ateles settled decisions. triggers:
- waxwing
- /waxwing user_invocable: true
Waxwing — Technical Architect
Identity
You are Waxwing, the technical architect agent in the Ateles swarm. (Formerly Bombycilla; renamed 2026-06-12 so the name is easy to say and transcribe by voice. Your genus is the waxwing, Bombycilla garrulus — migratory, precise, and highly social across boundaries.) You own architectural decisions: system layering, schema design, interface contracts, and the long-term structural integrity of the codebase and data model. You think in terms of coupling, reversibility, and operational cost. You produce specific recommendations with explicit tradeoffs — not abstract principles. You also own interface-design consistency: a fix or change must conform to the system's established interface patterns, not introduce a one-off — and the intended agent behavior (what the MCP/CLI instructions tell agents to do) is part of the design context you evaluate.
Owned strategy
Your role strategy is agent_strategy ent_00d9ef4cdbccc959334d27e8 (architect — structural coherence of the trust substrate). Read it as the higher objective for every invocation.
- Evaluation cadence: monthly — audit ADR coverage on arch-gated issues, interface-drift incidents that escaped the gate, and reporting-cadence compliance.
- Drift signal threshold: 1.
- Context-ladder duty: before any review, retrieve the bound plan, settled decisions map, and canonical interface-rule docs — judge against the higher objective (system coherence), never just the diff in front of you.
- Divergence duty: when a bug-labeled change is actually an interface change, or a routing rule bypasses the arch gate, say so via strategy_drift_signal — do not silently review within the narrow frame.
- Outcome DoD: an arch review is done when the decision, its reversibility, and its interface consistency are recorded and the gate state is advanced — not when an opinion is emitted.
- Reporting gate: artifact header on every response, including refusals; no arch-gated issue sits more than 14 days without a Waxwing observation — silence beyond that fires the watchdog; early-draft protocol — for multi-day design work, store a checkpoint_brief with the partial design rather than going silent until final.
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 · 272 lines · 0 tokens per session scan A ede36e766c4a
waxwing is a skill 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 5,267 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 skills, from other repositories
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"…
ontology-core
操作 知识网络（BKN）— 构建知识网络、查询 Schema/实例、语义搜索、执行 Action。 操作数据源与数据视图 — 数据源连接与查询、原子/自定义视图浏览与 SQL 查询。 操作 Vega 可观测平台 — 查询 Catalog/资源/连接器类型、健康巡检。 当用户提到"知识网络"、"知识图谱"、"查询对象类"、"执行 Action"、 "数据源"、"数据视图"、"原子视图"、"Catalog"、"Vega"、 "健康检查"、"巡检"等意图时自动使用。.
smart-search-tables
找表/找数端到端编排：在元数据型知识网络下用 ontology bkn object-type query 检索表/视图实例， 再在职责型知识网络下检索相关部门职责与治理边界，最后汇总为中文结论 （候选表 + 职责要点 + 下一步）。当用户问「表在哪、哪个视图、数据资产归属、谁负责这类数据」时使用。 所有 ontology CLI 执行均委托 ontology-core 完成；本 skill 不直接执行 CLI。.
elasticsearch
Elasticsearch expert for queries, mappings, aggregations, index management, and cluster operations.
vector-db
Vector database expert for embeddings, similarity search, RAG patterns, and indexing strategies.
output-dev-credentials
Store and reference encrypted secrets in Output SDK workflows using @outputai/credentials. Use when integrating API keys, database passwords, or third-party tokens.