gdd-token-auditor

gdd-token-auditor is an agent for Claude Code from 0martinez/get-design-done. It costs 38 tokens per session (508 once invoked), scanned A, original, MIT.

An assistant that checks whether a rendered design follows its defined design tokens, which are shared values for colors, type sizes, spacing, corners, and shadows.

In plain words
What is it for?
Use it to compare rendered designs and computed styles with TOKENS.md, calculate compliance, and report mismatches and inconsistencies.
Why use it?
It finds one-off values and inconsistent styling that can make different screens or design phases look unrelated.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md).

Good fit Use it to compare rendered designs and computed styles with TOKENS.md, calculate compliance, and report mismatches and inconsistencies.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/0martinez/get-design-done/gdd-token-auditor
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.

Clone the repo
git clone --depth 1 https://github.com/0martinez/get-design-done

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 gdd-token-auditor

README.md
[![agentmods](https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-token-auditor.svg)](https://agentmods.dev/agents/0martinez/get-design-done/gdd-token-auditor)
Your own site
<a href="https://agentmods.dev/agents/0martinez/get-design-done/gdd-token-auditor"><img src="https://agentmods.dev/badge/agents/0martinez/get-design-done/gdd-token-auditor.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 508 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 $0.00038 $0.00508
Opus 5 $0.00019 $0.00254
Sonnet 5 $0.00008 $0.00102
Haiku 4.5 $0.00004 $0.00051

Measured 7d ago against content hash 08b553df604b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

gdd-token-auditor 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 7d 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/gdd-token-auditor.md · 64 lines

What it actually says

<execution_flow>

  1. Parse TOKENS.md into a token map (name → value)
  2. For each rendered phase: a. Read RENDERED.md and SPEC.md b. Extract all color, font-size, spacing, radius, and shadow values used c. Compare each value against the token map d. Flag any value that doesn't match a token e. Check for inconsistent token usage (same element, different tokens across phases)
  3. If design tool is connected: a. Use get_styles to read computed CSS values b. Compare computed values against token map
  4. Calculate compliance score per phase and overall
  5. Write audit report </execution_flow>

<output_format> Return a structured audit:

# Token Audit Report

## Overall Compliance: XX%

## Per-Phase Compliance
| Phase | Compliance | Off-System Values |
|-------|-----------|-------------------|

## Off-System Values Found
| Phase | Element | Property | Value Used | Nearest Token | Distance |
|-------|---------|----------|-----------|---------------|----------|

## Cross-Phase Inconsistencies
| Element | Phase A Token | Phase B Token | Resolution |
|---------|--------------|---------------|-----------|

## Recommendations
- [specific, actionable recommendations]

</output_format>

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. 7d ago First seen · 64 lines · 38 tokens per session scan A 08b553df604b

Subscribe to this mod's changes

gdd-token-auditor is an agent published in the GitHub repository 0martinez/get-design-done (5 stars, last pushed 6mo ago), licensed MIT. It adds 38 tokens to every session and 508 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 2026-08-31.