agentmods.dev

gogh-secretary

gogh-secretary is an agent for Claude Code, Codex from AgriciDaniel/gogh. It costs 93 tokens per session (1,207 once invoked), scanned A, original, Apache-2.0.

A dedicated assistant for Gogh, a source-cited system that combines six frontend design guides. It answers design-stack questions and maintains the related Obsidian notes and research.

In plain words
What is it for?
Use it to choose skills for a website, compare captured guidance, refresh research, maintain the Gogh vault, or get a cited answer about its design rules.
Why use it?
It provides one place to ask which design guidance fits a task while keeping answers tied to source notes and their dates. It also helps detect outdated research.

Agent for Claude CodeCodex

Written for Claude Code and Codex: shipped in a Claude Code plugin, but also runs codex exec. Also seen: mentions AGENTS.md; mentions Codex.

Needs its repository: it runs a file that does not travel with it, so clone the repository first. The line is python scripts/render_stack_advisor.py --brief <project-brief.json> --registry references/skill-registry.json --out <report.md>.

Part of the gogh plugin — 7 skills, 1 agent shipped together

not rated 58repo +2 1mo ago A scan 93 tokens original Apache-2.0

Good fit Use it to choose skills for a website, compare captured guidance, refresh research, maintain the Gogh vault, or get a cited answer about its design rules.

Compare 6 agents from other repositories ↓
View source ↗ AgriciDaniel/gogh agricidaniel.github.io
Install

Getting it into your agent

It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.

Clone the repo
git clone --depth 1 https://github.com/AgriciDaniel/gogh
agentmods
npx agentmods add agents/agricidaniel/gogh/gogh-secretary

Made for: Claude Code, Codex.

Or install gogh, the plugin that ships this one along with the rest of its 7 skills, 1 agent.

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 gogh-secretary

README.md
[![agentmods](https://agentmods.dev/badge/agents/agricidaniel/gogh/gogh-secretary/github.svg)](https://agentmods.dev/agents/agricidaniel/gogh/gogh-secretary)
Your own site
<a href="https://agentmods.dev/agents/agricidaniel/gogh/gogh-secretary"><img src="https://agentmods.dev/badge/agents/agricidaniel/gogh/gogh-secretary/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 gogh-secretary

Your own site · 80×15
<a href="https://agentmods.dev/agents/agricidaniel/gogh/gogh-secretary"><img src="https://agentmods.dev/badge/agents/agricidaniel/gogh/gogh-secretary.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,207 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 $0.00093 $0.01207
Opus 5 $0.00046 $0.00603
Sonnet 5 $0.00019 $0.00241
Haiku 4.5 $0.00009 $0.00121

Measured 9d ago against content hash 715615b90baf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

gogh-secretary 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 9d 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/gogh-secretary.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Gogh Secretary

You are the owner's dedicated Gogh Secretary, grounded in the market-ready Gogh brain at ~/Desktop/Gogh. Gogh turns six frontend design skills into one source-cited advisory brain for AI coding agents.

Always do this first

Read ~/Desktop/Gogh/AGENTS.md, then the vault in this order:

  1. wiki/hot.md
  2. wiki/index.md
  3. The relevant folder hub _index.md
  4. The specific note, canvas, or deliverable

Answer from the brain first. Cite the note, its confidence tag, and dated source evidence. Never invent rules, thresholds, dials, licenses, versions, or audit criteria absent from the six captured skills.

How you work

  • Brain first. Use the root brain, wiki notes, source ledger, claim ledger, skill registry, and adapter manifest before reaching outside the corpus.
  • Dated citations. Cite retrieved dates and refresh_due dates from references/source-ledger.json or the relevant source note. Anything past refresh_due is stale until re-verified.
  • Six-skill boundary. Gogh covers taste-skill v2, make-interfaces-feel-better, Impeccable, Anthropic frontend-design, ui-ux-pro-max, and Vercel web-design-guidelines. Do not merge outside advice into canon without a dated source and an explicit ledger row.
  • Conflict handling. The brain records conflicts between skills rather than resolving them by fiat. State the conflict, the project context, and the cited basis for any recommendation.

Stack advice

Use a project brief and render advice through the adapter:

python scripts/render_stack_advisor.py --brief <project-brief.json> --registry references/skill-registry.json --out <report.md>

The report should recommend which skills apply, execution order, taste and motion guidance, risks, conflicts, source coverage, and audit checkpoints.

Upstream watch

Use scripts/import_skill_capture.py for capture work:

python scripts/import_skill_capture.py parse <capture.md> --out <parsed.json>
python scripts/import_skill_capture.py diff --old <old-capture.md> --new <new-capture.md>
python scripts/import_skill_capture.py build-registry --raw-dir .raw/skills --manifest .raw/.manifest.json --out references/skill-registry.json

Read the full file on GitHub · 123 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. 9d ago First seen · 123 lines · 93 tokens per session scan A 715615b90baf

Subscribe to this mod's changes

gogh-secretary is an agent published in the GitHub repository AgriciDaniel/gogh (58 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 93 tokens to every session and 1,207 once invoked, about $0.0005 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.

Design and UXResearch
Related

Other agents, from other repositories

ux-flow-auditor

Use this agent when the user mentions UX flow issues, dead-end views, dismiss traps, missing empty states, broken user journeys, or wants a UX audit of their iOS app. Automatically scans SwiftUI and UIKit code for user journey defects - detects dead ends, dismiss traps, buried CTAs, missing loading/error/empty states…

CharlesWiltgen/Axiom · 190 tokens

ijfw-accessibility-reviewer

Design-phase WCAG 2.1 AA review of UI artefacts: contrast, semantics, focus, ARIA. Trigger per design review pass.

FerroxLabs/ijfw · 37 tokens

Design System Auditor

Design system accessibility auditor. Validates color tokens, CSS custom properties, Tailwind config, and design token files (Style Dictionary, tokens.json) for WCAG AA/AAA contrast compliance. Catches contrast failures at the token source before they reach deployed UI. Also validates focus ring tokens (WCAG 2.4.13…

Community-Access/accessibility-agents · 109 tokens

design

Design system generator — maps product domain to style, palette, typography, anti-patterns. Creates .rune/design-system.md. Use BEFORE any frontend code generation.

Rune-kit/rune · 35 tokens

mobile-ux-optimizer

Use this agent when you need to optimize UI/UX components or interfaces for mobile-first experiences, analyze existing design themes, or ensure mobile usability standards are met. Examples: Context: User has created a desktop-focused component and needs it optimized for mobile. user: 'I've built this navigation…

xbim08/awesome-claude-code-plugins · 0 tokens

frontend-reviewer

Reviews interface, branding and copy. Always verifies against a screenshot and the rendered DOM, never by reading CSS or HTML.

everywan-dev/claude-code-engineering · 28 tokens