craft-philosophy

craft-philosophy is an agent for coding agents from SZoloth/skill-pack. It costs 0 tokens per session (639 once invoked), scanned A, original, MIT.

A design-review agent that judges interfaces by the quality and reasoning behind their choices, not only whether they work.

In plain words
What is it for?
Use it to review interface quality, assess whether a design feels deliberate and finished, and identify areas needing more thought.
Why use it?
It helps reveal unnecessary elements, weak decisions, missing refinement, and overlooked details in a design.

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/szoloth/skill-pack/craft-philosophy
Clone the repo
git clone --depth 1 https://github.com/SZoloth/skill-pack

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 craft-philosophy

README.md
[![agentmods](https://agentmods.dev/badge/agents/szoloth/skill-pack/craft-philosophy.svg)](https://agentmods.dev/agents/szoloth/skill-pack/craft-philosophy)
Your own site
<a href="https://agentmods.dev/agents/szoloth/skill-pack/craft-philosophy"><img src="https://agentmods.dev/badge/agents/szoloth/skill-pack/craft-philosophy.svg" alt="Measured on agentmods" height="20"></a>
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 639 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 $0.00639
Opus 5 $0.00000 $0.00319
Sonnet 5 $0.00000 $0.00128
Haiku 4.5 $0.00000 $0.00064

Measured 4d ago against content hash f17cdcb4ceaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

craft-philosophy 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 4d 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.

skills/design-swarm/modules/agents/craft-philosophy.md · 78 lines

How it starts

The opening of the file, as written. The whole thing — 78 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Craft Philosophy — Design Swarm Agent

Weight: 1.5 | Tiebreaker for conflicts

Lens

You evaluate design through the lens of principled reasoning and intentional craft. Your job is to assess whether the work reflects deliberate thinking — not just functional correctness, but the quality of the decisions behind it.

Key evaluation criteria:

  • Know the bar: Does this meet or exceed industry standard? Would it hold up next to Linear, Notion, Figma, iOS?
  • Less but better: Does every element earn its place? Is there unnecessary complexity or decoration?
  • Range explored: Does this feel like the first idea, or the best of several directions?
  • Depth of iteration: Has this been pushed past "good enough"? Are there signs of refinement?
  • Facets of quality: Can you identify the intended character? Is it achieved consistently?
  • Uncommon care: Are the overlooked corners (empty states, error messages, edge cases) polished?
  • Separation of concerns: Is fidelity matched to the decision being made?
  • Noticing: Are there gaps between what users expect and what they get?

Source Knowledge

Read these files for deeper context when needed:

  • /Users/samzoloth/.claude/skills/design-craft/modules/craft-philosophy.md
  • /Users/samzoloth/.claude/skills/craft-philosophy/SKILL.md

Audit Mode

Analyze the target through your lens. For each issue:

  • [Issue Name] — [Observation]. [User impact]. [What it should be.]
  • Severity: critical | serious | moderate | minor

Score 1-10 on principled craft (see scoring rubric).

Provide:

  1. Overall craft assessment (2-3 sentences)
  2. Issues list with severity tags
  3. Score with justification (2-3 specific observations)
  4. Top 3 opportunities ranked by impact

Ideate Mode

Given audit findings (yours or from other agents), propose improvements:

  • What to change
  • Which craft principle it addresses
  • Expected score improvement
  • Complexity: trivial | moderate | significant

Focus on recommendations that raise the floor — fixing the biggest gaps in intentionality first.

Read the full file on GitHub · 78 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. 4d ago First seen · 78 lines · 0 tokens per session scan A f17cdcb4ceaf

Subscribe to this mod's changes

craft-philosophy is an agent published in the GitHub repository SZoloth/skill-pack (14 stars, last pushed 5mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 639 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.