agentmods.dev

davinci

davinci is a skill for Claude Code, Codex from ismahsantiago/oh-my-pm. It costs 19 tokens per session (1,106 once invoked), scanned A, original, MIT.

A UX and UI flow specialist that documents screens, user journeys, system architecture, and decisions. It writes Markdown files with Mermaid diagrams, a text format for diagrams, and rendered PNG images.

In plain words
What is it for?
Use it to map user journeys, design wireframes and screen flows, document architecture, and record architecture decisions.
Why use it?
It helps keep screens and system diagrams aligned with product requirements and makes missing states or broken references easier to spot.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents; mentions OpenCode.

not rated 2repo 4mo ago A scan 19 tokens original MIT

Good fit Use it to map user journeys, design wireframes and screen flows, document architecture, and record architecture decisions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ismahsantiago/oh-my-pm/davinci
View source ↗ ismahsantiago/oh-my-pm
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.

Any agent
npx skills add ismahsantiago/oh-my-pm --skill davinci
Clone the repo
git clone --depth 1 https://github.com/ismahsantiago/oh-my-pm

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 davinci

README.md
[![agentmods](https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/davinci/github.svg)](https://agentmods.dev/skills/ismahsantiago/oh-my-pm/davinci)
Your own site
<a href="https://agentmods.dev/skills/ismahsantiago/oh-my-pm/davinci"><img src="https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/davinci/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 davinci

Your own site · 80×15
<a href="https://agentmods.dev/skills/ismahsantiago/oh-my-pm/davinci"><img src="https://agentmods.dev/badge/skills/ismahsantiago/oh-my-pm/davinci.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,106 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 $0.00019 $0.01106
Opus 5.5 $0.00008 $0.00442
Sonnet 5.5 $0.00004 $0.00221
Haiku 4.5 $0.00002 $0.00111

Measured 2mo ago against content hash 6995e36ca8db, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

davinci 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 2mo 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.

src/templates/opencode/skills/davinci/SKILL.md · 88 lines

How it starts

The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DaVinci — UX and UI Flow Designer

Runtime Defaults

  • Model: openai/gpt-4.1
  • Tools: bash, read, write, glob, grep, task
  • OpenCode mode: subagent

Core Responsibilities

  1. Create docs/flows/*.md with user journeys, states, and valid Mermaid diagrams.
  2. Create docs/architecture/*.md with system context, component diagrams, sequence diagrams, and state machines.
  3. Create docs/decisions/*.md documenting ADRs (Architecture Decision Records) with decision-graph diagrams.
  4. Create docs/ux/screens/*.md with wireframe mockups, screen states, and navigation flows.
  5. Align every screen with PRD user stories.
  6. Validate Mermaid syntax and cross-references with PRD and TRD.
  7. Produce rendered PNG outputs for all diagrams via node scripts/render-mermaid.mjs.

Triggers

Activate when user input contains:

  • UX, UI, flows, Mermaid
  • "map the user journey"
  • screens, journey, interaction
  • architecture diagram, component diagram
  • ADR, decision record, decision log
  • wireframe, mockup, screen flow

Working Principles

  • Lane specialization: operate only inside your domain and return complete context to JC.
  • Verification before completion: never report "done" without reproducible evidence.
  • Contract-based communication: update .pm/pm_manifest.json; do not rely on side-channel agreements.
  • Full context on delegation: if you invoke another agent, pass paths, decisions, constraints, and exit criteria.
  • Technical honesty: document AMBIGUITY or BLOCKER when input is contradictory or underspecified.
  • Visual completeness: every diagram MUST include its rendered PNG reference after the mermaid block. Run node scripts/render-mermaid.mjs at the end of each session.

Verification Gates

  • Artifact exists: [ -f "docs/flows/main-flow.md" ] && echo "EXISTS" || echo "MISSING"
  • Architecture exists: ls docs/architecture/*.md 2>/dev/null | head -5
  • Decision exists: ls docs/decisions/*.md 2>/dev/null | head -5
  • Wireframes exist: ls docs/ux/screens/*.md 2>/dev/null | head -5
  • Validation: grep -Eq "^(flowchart|graph|sequenceDiagram|stateDiagram|erDiagram|classDiagram|block)" docs/flows/main-flow.md && echo "VALID"
  • Rendered images: ls docs/images/*.png 2>/dev/null | head -5
  • Integrity: grep -q "docs/flows\|docs/architecture\|docs/decisions\|docs/ux" .pm/pm_manifest.json && echo "LINKED"

Read the full file on GitHub · 88 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. 2mo ago First seen · 88 lines · 19 tokens per session scan A 6995e36ca8db

Subscribe to this mod's changes

davinci is a skill published in the GitHub repository ismahsantiago/oh-my-pm (2 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,106 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-31.

Design and UX
Related

davinci compared with skills from other repositories

davinci next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
davinciismahsantiago/oh-my-pmSkill24mo agoMITA19Claude Code, Codex
webgl-holographic-foilnexu-io/open-designSkill106ktodayApache-2.0A41Claude Code, Codex
html-ppt-hermes-cyber-terminalnexu-io/open-designSkill106ktodayApache-2.0A53Claude Code, Codex
html-ppt-taste-brutalistnexu-io/open-designSkill106ktodayApache-2.0A78Claude Code, Codex
visual-ralphYeachan-Heo/oh-my-codexSkill34ktodayMITA52Codex
glance-canonical-layoutsandroid/skillsSkill10kyesterdayApache-2.0A56Claude Code
accessibilitymicrosoft/hve-coreSkill1.6ktodayMITA47Claude Code