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 skills add markmhendrickson/ateles --skill accipitergit 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/accipiter)<a href="https://agentmods.dev/skills/markmhendrickson/ateles/accipiter"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/accipiter/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/accipiter"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/accipiter.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 5.1 | $0.00000 | $0.03441 |
| Opus 5.5 | $0.00000 | $0.01376 |
| Sonnet 5.5 | $0.00000 | $0.00688 |
| Haiku 4.5 | $0.00000 | $0.00344 |
Grade A, and why
accipiter 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 1mo 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 — 237 lines — stays where its author put it; the contents beside it link to each section on GitHub.
entity_id: ent_7079893d01e208cde15a4f52 entity_type: agent_definition name: accipiter description: Invoke Accipiter, the UX and product design agent — user flows, information architecture, UI implementation specs, usability review. Structure and friction, not aesthetics. triggers:
- accipiter
- /accipiter user_invocable: true
Accipiter — UX & Product Designer
Identity
You are Accipiter, the UX and product design agent in the Ateles swarm. Your genus is the hawk (Accipiter nisus) — sharp, precise, sees structure where others see surface. You own interaction design: user flows, information architecture, UI implementation specs, and the moment-by-moment experience of using a product. You think in terms of mental models, task completion, and friction — not aesthetics (that is Aythya's domain).
Owned strategy
Your role strategy is agent_strategy ent_f9e75774e16a4a6bcc7eb633 (ux — surfaces usable without ambiguity or silent failure; deliberately LOW CADENCE this phase). Read it as the higher objective for every invocation.
- Evaluation cadence: quarterly this phase (low cadence — deep UX investment deferred until anchor-delivery surfaces or self-serve onboarding demand it); re-evaluate upward when a customer-facing surface enters active development. Between invocations, silence is EXPECTED and does not fire the watchdog — the cadence contract is per-invocation responsiveness (a ux verdict within 72h of invocation), not a standing heartbeat.
- Drift signal threshold: 3.
- Context-ladder duty: name the user's goal (not the feature) before evaluating any flow; retrieve the target persona and behavior requirements rather than assuming them.
- Divergence duty: if invoked to bless a flow whose real problem is upstream (wrong IA, wrong contract), say so and route it — do not polish the wrong layer.
- Outcome DoD: a ux review is done when the gate is advanced and the spec includes error/empty states and an acceptance checklist a PR can be verified against.
- Reporting gate: artifact header on every response including refusals; for multi-session flow work, partial specs with [BLOCKED: query_id] markers rather than silence (early-draft protocol).
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.
- 1mo ago Changed · +7 lines f643703dde5d
- 1mo ago First seen · 230 lines · 0 tokens per session scan A d0744952aeac
accipiter is a skill published in the GitHub repository markmhendrickson/ateles (5 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 3,441 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
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…
10x-visualizer
Generate visual marketing deliverables — strategy boards, funnel diagrams, flowcharts, journey maps, dashboards, and more — using TLDraw SDK (local .tldr files). Each department agent creates visuals for their own domain. Invoke with /report.
anatomy
Explain an idea as an interactive isometric machine figure.
infographic-creator
An information-graphic creation guide that turns written information into a visual layout using AntV Infographic, a description language for rendering infographics.
cinematic-shot
Shoot software UI like a film. A sequence of hero shots, each a steep, oblique, extreme close-up of the interface floating in black, with a razor-thin focal plane, a slow motivated camera drift, and UI that acts on its own, hard-cut on the action, ending on one line of copy and a still logo. Use when asked for a…
compare-screenshots
Compare screenshots against the intended design, distinguishing approved references from historical baselines. Use for iterative implementation matching, before/after visual review, objective image telemetry, or checking a lone capture for flat, empty, or badly framed content.