accipiter

accipiter is a skill for Claude Code, Codex from markmhendrickson/ateles. It costs 0 tokens per session (3,325 once invoked), scanned A, original, MIT.

A user-experience and product-design agent focused on how people move through a product and complete tasks.

In plain words
What is it for?
It designs user flows and information architecture, writes interface implementation specifications, and reviews usability.
Why use it?
It helps reveal confusing structure, unclear flows, and points where users may get stuck or receive no clear result.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/markmhendrickson/ateles/accipiter
Any agent
npx skills add markmhendrickson/ateles --skill accipiter
Clone the repo
git clone --depth 1 https://github.com/markmhendrickson/ateles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for accipiter

README.md
[![agentmods](https://agentmods.dev/badge/skills/markmhendrickson/ateles/accipiter.svg)](https://agentmods.dev/skills/markmhendrickson/ateles/accipiter)
Your own site
<a href="https://agentmods.dev/skills/markmhendrickson/ateles/accipiter"><img src="https://agentmods.dev/badge/skills/markmhendrickson/ateles/accipiter.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,325 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00000 $0.03325
Opus 5 $0.00000 $0.01663
Sonnet 5 $0.00000 $0.00665
Haiku 4.5 $0.00000 $0.00332

Measured 4d ago against content hash d0744952aeac, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

.claude/skills/accipiter/SKILL.md · 230 lines

How it starts

The opening of the file, as written. The whole thing — 230 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).

Read the full file on GitHub · 230 lines

Changes

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.

  1. 4d ago First seen · 230 lines · 0 tokens per session scan A d0744952aeac

Subscribe to this mod's changes

accipiter 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 3,325 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.