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.
npx agentmods add skills/prosusai/prism/mine-designnpx skills add ProsusAI/prism --skill mine-designgit clone --depth 1 https://github.com/ProsusAI/prismWrote 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.
[](https://agentmods.dev/skills/prosusai/prism/mine-design)<a href="https://agentmods.dev/skills/prosusai/prism/mine-design"><img src="https://agentmods.dev/badge/skills/prosusai/prism/mine-design.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00097 | $0.03379 |
| Opus 5 | $0.00048 | $0.01690 |
| Sonnet 5 | $0.00019 | $0.00676 |
| Haiku 4.5 | $0.00010 | $0.00338 |
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 6d 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.
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.mdcheck. - 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.
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.
- 6d ago First seen · 280 lines · 97 tokens per session scan A 2e748914f448
mine-design is a skill published in the GitHub repository ProsusAI/prism (20 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 97 tokens to every session and 3,379 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…