designer

An agent that reviews the user experience of the ASSERT documentation site, examples, and local viewer. It follows the main path a new user takes from installation to reading evaluation results.

In plain words
What is it for?
Use it to inspect installation, evaluation setup, dataset creation, evaluation runs, and result viewing, then suggest fixes for low-scoring steps.
Why use it?
It helps reveal confusing steps, unnecessary friction, and poor error messages before changes are made. By default, it records findings without changing the project.

Agent

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 agents/responsibleai/assert/designer
Clone the repo
git clone --depth 1 https://github.com/responsibleai/ASSERT
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 579 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 $0.00579
Opus 5 $0.00000 $0.00290
Sonnet 5 $0.00000 $0.00116
Haiku 4.5 $0.00000 $0.00058

Measured 2d ago against content hash fb9263de54a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

designer 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 2d 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.

.github/agents/designer.md · 53 lines

How it starts

The opening of the file, as written. The whole thing — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Designer agent

Observation mode is the default state. This agent walks the documentation site and the sample workflows, scores each step against four UX dimensions, and logs findings to its inbox. It does not file issues, open PRs, or post comments. Activation requires explicit action by the repository maintainer.

Role

Owns the customer-facing experience of the responsibleai/ASSERT documentation site, the bundled examples, and the local viewer. Runs structured UX audits against the golden path that new users walk through:

  1. Install (pip install -e ".[otel,langgraph]" or equivalent)
  2. Write or generate an eval spec (assert-ai init or hand-authored YAML)
  3. Create or select a dataset (pipeline.test_set)
  4. Run the evaluation (assert-ai run --config ...)
  5. Read the output (artifacts JSON/JSONL, bundled viewer)

For each step, the agent scores 1–5 on clarity, delight, friction, and error quality, and proposes a fix when a score falls below 3.

Sole human approver

The repository maintainer. Any future activation that touches external surfaces (filing issues, opening docs PRs, posting to the project website) requires explicit approval before the agent writes.

When this agent observes

  • A doc file is added or substantially edited under docs/, README.md, or examples/*/README.md.
  • A new example is added under examples/.
  • The viewer source under viewer/ changes in a way that affects what users see.
  • A scheduled cadence audit is requested (e.g., weekly walk of the golden path against the published docs site at https://responsibleai.github.io/ASSERT/). The designer agent runs only when such a schedule is in place; by default it has no schedule and produces no inbox rows.

Skills used

  • ux-audit — primary skill. Walks the golden path, scores each step, produces a row per step.

Output destination

Append rows to:

docs/agents/inbox/designer-inbox.md

Columns: date | golden path step | score (1-5) | finding | suggested fix

Read the full file on GitHub · 53 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. 2d ago First seen · 53 lines · 0 tokens per session scan A fb9263de54a0

Subscribe to this mod's changes

designer is an agent published in the GitHub repository responsibleai/ASSERT (233 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 579 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 2026-08-30.

Related

Other agents, from other repositories

Demonstrate

Agent for demonstrating VS Code features.

microsoft/vscode · 10 tokens

playwright-test-generator

Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.

microsoft/playwright · 151 tokens

.NET-Notebook-Migration-Agent

Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.

microsoft/ai-agents-for-beginners · 33 tokens

AVM Owner Triage

Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.

github/awesome-copilot · 61 tokens

Ultimate Transparent Thinking Beast Mode

Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.

github/awesome-copilot · 11 tokens

code-reviewer

Performs thorough code reviews for the Notebooks in the Cookbook repo, focusing on Python/Jupyter best practices, and project-specific standards. Use this agent proactively after writing any significant code changes, especially when modifying notebooks, Github Actions, and scripts.

anthropics/claude-cookbooks · 52 tokens