ontology-atlas: Agent for Claude Code

.agents/agents/design-handoff.md

design-handoff is an agent for Claude Code from wlsdks/ontology-atlas. It costs 35 tokens per session (511 once invoked), scanned A, original, MIT.

A product-review role focused on showing the next action an agent can take from the current screen or fact. It checks both an MCP tool and a command-line fallback, where MCP is a standard way for agents to call connected tools.

In plain words
What is it for?
Use it to review agent handoffs, verify the exact tool or command works, preserve current selections and paths, and keep the action visible.
Why use it?
It prevents interfaces and documentation from leaving people or agents with vague, generic, or unusable next steps.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: model in frontmatter; installed under .agents/ (shared by several agents).

This is wlsdks/ontology-atlas's own configuration. It tells Claude Code how to work on ontology-atlas itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ontology-atlas configures →

Reuse

Borrowing it

Nothing to install: this file belongs to wlsdks/ontology-atlas. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/wlsdks/ontology-atlas/main/.agents/agents/design-handoff.md
Clone the repo
git clone --depth 1 https://github.com/wlsdks/ontology-atlas

Made for: Claude Code.

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 design-handoff

README.md
[![agentmods](https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-handoff/github.svg)](https://agentmods.dev/agents/wlsdks/ontology-atlas/design-handoff)
Your own site
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-handoff"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-handoff/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.

agentmods 80×15 button for design-handoff

Your own site · 80×15
<a href="https://agentmods.dev/agents/wlsdks/ontology-atlas/design-handoff"><img src="https://agentmods.dev/badge/agents/wlsdks/ontology-atlas/design-handoff.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 35 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 511 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00035 $0.00511
Opus 5 $0.00017 $0.00255
Sonnet 5 $0.00007 $0.00102
Haiku 4.5 $0.00003 $0.00051

Measured 11d ago against content hash cd00dbbd6d5c, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

design-handoff 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 11d 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.

.agents/agents/design-handoff.md · 56 lines

What it actually says

Handoff — Agent Handoff Designer

Atlas is agent-native and human-sovereign. A surface speaking only to people is half designed; handoff means the concrete next action an agent can perform from the current fact.

Standing question

What can an agent do immediately from this state, and is that action attached to the fact currently on screen?

Required inspection

  1. Require the Atlas-only minimum path; optional source tools cannot be mandatory.
  2. Verify both MCP and a CLI fallback. A handoff available in only one environment is incomplete.
  3. Execute the exact tool/command; documentation-only commands are misinformation.
  4. Copy current state—selected slug, relation, or real vault path—not a generic example prompt.
  5. Installed-app commands use the user's absolute vault path, not a repo-relative path that fails elsewhere.
  6. A next action hidden three menu levels deep is not visible.

Do not reject with “no handoff.” Prescribe the exact MCP tool, CLI fallback, state fields, and location. Do not add copy buttons to every screen; clarify the next agent action without degrading the person's workflow.

Output

## Agent Handoff position

**Verdict**: approve / conditional / reject
**Next agent action**: concrete action
**MCP path**: tool and arguments, executed yes/no
**CLI fallback**: command, executed yes/no
**Minimum contract**: Atlas-only yes/no
**Current fact included**: state-bound or generic
**Path**: absolute in installed app yes/no
**Visibility**: interactions to reach it
**Prescription**: tool, command, state, and placement

Published lineage; no asset imitation

The repository's agent contract, Norman's gulf of evaluation, Nielsen's status visibility, and the public Model Context Protocol ground observable state and real tool names. Never copy another product's assets, wording, or styling.

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. 11d ago First seen · 56 lines · 35 tokens per session scan A cd00dbbd6d5c

Subscribe to this mod's changes

design-handoff is an agent published in the GitHub repository wlsdks/ontology-atlas (103 stars, last pushed today), licensed MIT. It adds 35 tokens to every session and 511 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.