mine-design

mine-design is a skill for Claude Code, Codex from ProsusAI/prism. It costs 97 tokens per session (3,379 once invoked), scanned A, original, Apache-2.0.

A workflow that reads a codebase’s current source and records its design decisions, trade-offs, unusual behaviors, and architectural patterns in _analysis/design.md.

In plain words
What is it for?
Starting design analysis, using existing analysis files for orientation, and preparing findings for a later practice-synthesis step.
Why use it?
It captures reasoning that may exist only in the code, making important choices easier to review and turn into future development guidance.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions CLAUDE.md; mentions Claude Code.

Good fit Starting design analysis, using existing analysis files for orientation, and preparing findings for a later practice-synthesis step.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/prosusai/prism/mine-design
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 ProsusAI/prism --skill mine-design
Clone the repo
git clone --depth 1 https://github.com/ProsusAI/prism

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 mine-design

README.md
[![agentmods](https://agentmods.dev/badge/skills/prosusai/prism/mine-design/github.svg)](https://agentmods.dev/skills/prosusai/prism/mine-design)
Your own site
<a href="https://agentmods.dev/skills/prosusai/prism/mine-design"><img src="https://agentmods.dev/badge/skills/prosusai/prism/mine-design/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 mine-design

Your own site · 80×15
<a href="https://agentmods.dev/skills/prosusai/prism/mine-design"><img src="https://agentmods.dev/badge/skills/prosusai/prism/mine-design.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 97 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,379 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 $0.00097 $0.03379
Opus 5.5 $0.00039 $0.01352
Sonnet 5.5 $0.00019 $0.00676
Haiku 4.5 $0.00010 $0.00338

Measured 2mo ago against content hash 2e748914f448, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mine-design 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.

skills/mine-design/SKILL.md · 280 lines

How it starts

The opening of the file, as written. The whole thing — 280 lines — stays where its author put it; the contents beside it link to each section on GitHub.

When to use this skill

Snapshot-based design decisions for any codebase. Extract the reasoning behind current architectural choices, trade-offs made, and non-obvious system behaviors that live in the code itself — not in commit messages. Produce _analysis/design.md.


Step 1 — Orient

Check if _analysis/index.md already exists:

test -f _analysis/index.md && echo "FOUND" || echo "NOT_FOUND"

If _analysis/index.md exists: Also check for cluster files:

ls _analysis/cluster_*.md 2>/dev/null

Then ask the user:

"Found existing analysis files in _analysis/:

  • index.md {- cluster_*.md (list found files, if any)}

Use these for orientation, or run a fresh codebase scan? (Files may be outdated if the code has changed.)"

  • Use existing → Read _analysis/index.md. It contains the directory map, framework, entry points, and key file registry. Use it as your structural map and skip the bash commands below — go directly to the _analysis/directives.md check.
  • Fresh scan → Run the bash commands below.

If _analysis/index.md does not exist: Run the following to build a structural picture from scratch:

cat README.md 2>/dev/null || cat readme.md 2>/dev/null
cat CLAUDE.md 2>/dev/null
cat package.json 2>/dev/null || cat go.mod 2>/dev/null || cat requirements.txt 2>/dev/null || cat Cargo.toml 2>/dev/null
ls -1

Check if _analysis/directives.md already exists. If it does, skim it to note what subsystems it covers — you'll avoid producing directive-style content (imperative rules from git history) in this analysis.


Step 2 — Discover subsystems

From the directory structure and README, identify 4–8 major subsystems or concerns. Before proposing clusters, read at least one entry-point file (main file, index, CLI root, or server start) to confirm the runtime structure matches the directory structure.

If the user chose to use existing files in Step 1 and cluster files were found, skim them to extract subsystem names and their assigned files. Use these as the starting point — adjust or merge only where the cluster divisions do not map cleanly to design concerns.

Read the full file on GitHub · 280 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 · 280 lines · 97 tokens per session scan A 2e748914f448

Subscribe to this mod's changes

mine-design is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 3,379 once invoked, about $0.0004 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 2026-08-30.

Related

mine-design compared with skills from other repositories

mine-design next to 6 skills from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
mine-designProsusAI/prismSkill204mo agoApache-2.0A97Claude Code, Codex
imagegenopenai/codexSkill133kyesterdayApache-2.0A113Codex
playwright-climicrosoft/playwrightSkill99kyesterdayApache-2.0A19Claude Code
local-ai-agentsmicrosoft/ai-agents-for-beginnersSkill79k4d agoMITA200Claude Code, Codex
systematic-debuggingobra/superpowersSkill313k3d agoMITA21Claude Code
next-cache-components-adoptionvercel/next.jsSkill143kyesterdayMITA95Claude Code
next-partial-prefetching-adoptionvercel/next.jsSkill143kyesterdayMITA103Claude Code