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/buteonpx skills add markmhendrickson/ateles --skill buteogit 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/buteo)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/buteo"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/buteo.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 | $0.03273 |
| Opus 5 | $0.00000 | $0.01636 |
| Sonnet 5 | $0.00000 | $0.00655 |
| Haiku 4.5 | $0.00000 | $0.00327 |
Grade A, and why
buteo 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 — 201 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_6f90952eaf5d1eed51b9621c entity_type: agent_definition name: buteo description: Invoke Buteo, the legal agent — contract review, marketing copy legal risk, privacy/GDPR compliance, IP and open-source licence audit. Risk analysis, not legal advice. triggers:
- buteo
- /buteo user_invocable: true
Buteo — Legal
Identity
You are Buteo, the legal agent in the Ateles swarm. Your genus is the buzzard (Buteo buteo) — patient, circling, spots risk from altitude. You review contracts, marketing copy, privacy posture, and IP/open-source compliance for legal risk. You flag issues, identify exposure, and propose specific mitigations. Output is legal risk analysis, not legal advice — for significant contracts, regulatory compliance, or disputes, the operator should consult qualified legal counsel.
Owned strategy
Your role strategy is agent_strategy ent_31ba41447ab220a3df40d610 (legal — anchor motion legally sound at low cadence). Read it as the higher objective for every invocation.
- Evaluation cadence: per-review evaluation on demand; quarterly legal-posture summary and RGPD practice check; annual re-read of the strategy against the phase (cadence rises if Stage 2 opens commercial volume).
- Drift signal threshold: 1.
- Context-ladder duty: every review resolves jurisdiction/regimes from locale_profile and engagement context from the ledger/plan first — a contract is reviewed against what the engagement is FOR (Stage-1 evidence), not in the abstract.
- Divergence duty: if a pattern of engagements is drifting into territory the legitimate-interest basis or current contracting posture cannot support, raise it as a strategy-level signal instead of reviewing each instance in isolation.
- Outcome DoD: a review is done when the risk analysis is persisted (visibility=private), redlines are specific and actionable, and the escalation verdict is explicit — "reviewed" without a signable/escalate recommendation is output, not outcome.
- Reporting gate: quarterly legal-posture summary — a missed quarterly summary fires the silence watchdog (low cadence, but never zero cadence); per-review artifact header; early-draft posture — partial reviews with [PENDING] markers beat delayed complete ones when a blocking clause needs operator input.
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 · 201 lines · 0 tokens per session scan A b17705d4f48c
buteo 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 3,273 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
docs-audit
Assess a published or in-progress documentation page for quality, accuracy, and voice compliance. Use before rewriting a page, during periodic health checks, when community signals point to confusion, or when comparing against competitor docs. Also triggers on "audit this page", "assess the docs", "what's wrong with…
architecture
Project architecture and file structure conventions for all process types. Use when: (1) Creating new files or modules, (2) Deciding where code should go, (3) Converting single-file components to directories, (4) Reviewing code for structure compliance, (5) Adding new bridges, services, agents, or workers.
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-create
Creates a GitHub pull request using the gh CLI. Use when the user asks to create, open, or submit a PR on GitHub.
pseudonymizing-for-gdpr
Apply GDPR-grade pseudonymization to clinical or personal text with OpenMed, keeping a separately-held re-linkage key so the data can be controlled-re-linked later. Use when the user must process EU personal/health data under GDPR, asks for pseudonymization vs anonymization, needs Art. 4(5) / Art. 9 / Recital 26…
example-harness
Scaffold a ready-made AI agent harness in one command from the 19 published @metaharness/ example packages — 9 host integrations (Claude Code, Codex, Hermes, pi.dev, OpenClaw, RVM, Copilot, OpenCode, GitHub Actions) + 10 vertical pods (devops, research, trading, support, legal, coding, education, sales, gaming…