Borrowing it
Nothing to install: this file belongs to matteocervelli/llms. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/matteocervelli/llms/main/.claude/skills/discovery/SKILL.mdgit clone --depth 1 https://github.com/matteocervelli/llmsWrote 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/matteocervelli/llms/discovery)<a href="https://agentmods.dev/skills/matteocervelli/llms/discovery"><img src="https://agentmods.dev/badge/skills/matteocervelli/llms/discovery.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 | $0.00068 | $0.01345 |
| Opus 5 | $0.00034 | $0.00673 |
| Sonnet 5 | $0.00014 | $0.00269 |
| Haiku 4.5 | $0.00007 | $0.00135 |
Grade A, and why
discovery 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 3d 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 — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discovery — Phase 0 Validation Gate
Structured Discovery & Validation before committing to a feature. Prevents building unvalidated ideas by gating entry into the story and design pipeline with four sequential modes.
Usage
/discovery # Show overview of all 4 modes
/discovery problem # Problem framing: who has it, how urgent, what evidence
/discovery competitive # Competitive landscape: what exists, differentiators, moat
/discovery feasibility # Feasibility: technical, economic, time constraints
/discovery checkpoint # Go/no-go gate: 5-criteria verdict before /story create
Workflow
Step 1: Determine Mode
Parse $ARGUMENTS for explicit mode. If no arguments provided, show overview:
no args → read templates/overview.md
problem → read templates/problem/summary.md
competitive → read templates/competitive/summary.md
feasibility → read templates/feasibility/summary.md
checkpoint → read templates/checkpoint/summary.md
<anything else> → show usage error + list valid modes + read templates/overview.md
Step 2: Present Guidance (Progressive Disclosure)
Level 1 — Summary (default, ~20 lines): Read and present the summary template. This is the entry point — frames the questions to answer.
Level 2 — Patterns (on request, ~60 lines): When the user asks for more depth, "show me patterns", "how do I score this", or "give me examples" — read the patterns template.
Level 3 — Full Analysis (on request): No template — dive into specific questions with the user based on context provided.
Step 3: Run Modes Sequentially
Recommended sequence: problem → competitive → feasibility → checkpoint
Each mode builds on the previous:
- problem → frames who, what, and why
- competitive → validates market gap
- feasibility → validates buildability
- checkpoint → synthesizes all three into a go/no-go verdict
You can run individual modes out of order when the user has already done partial research.
What ships with it
9 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- templates/checkpoint/patterns.md 5.4 KB
- templates/checkpoint/summary.md 1.9 KB
- templates/competitive/patterns.md 3.3 KB
- templates/competitive/summary.md 1.3 KB
- templates/feasibility/patterns.md 4.0 KB
- templates/feasibility/summary.md 1.7 KB
- templates/overview.md 1.1 KB
- templates/problem/patterns.md 2.9 KB
- templates/problem/summary.md 1.3 KB
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.
- 3d ago First seen · 138 lines · 68 tokens per session scan A 4fff057a70ad
discovery is a skill published in the GitHub repository matteocervelli/llms (25 stars, last pushed 3mo ago), licensed MIT. It adds 68 tokens to every session and 1,345 once invoked, about $0.0003 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 2026-09-03.
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…