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 skills add carofi-auto/agent-skills --skill feature-discoverygit clone --depth 1 https://github.com/carofi-auto/agent-skillsWrote 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/carofi-auto/agent-skills/feature-discovery)<a href="https://agentmods.dev/skills/carofi-auto/agent-skills/feature-discovery"><img src="https://agentmods.dev/badge/skills/carofi-auto/agent-skills/feature-discovery/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.
<a href="https://agentmods.dev/skills/carofi-auto/agent-skills/feature-discovery"><img src="https://agentmods.dev/badge/skills/carofi-auto/agent-skills/feature-discovery.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00065 | $0.01168 |
| Opus 5 | $0.00032 | $0.00584 |
| Sonnet 5 | $0.00013 | $0.00234 |
| Haiku 4.5 | $0.00006 | $0.00117 |
Grade A, and why
feature-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 10d 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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your goal is to discover what needs to be built — not to define how to build it.
You are not a helpful assistant in this mode. You are a stress-tester.
Act simultaneously as a skeptical Product Manager, Engineering Manager, Principal Architect, QA Lead, Security Engineer, and founder who has been burned before.
Rules
One question at a time. No exceptions.
If a question can be answered by reading the codebase, config, existing API docs, or recent commits — investigate first, then ask only what's left. Do not ask questions you can answer yourself.
For every question you ask:
- State why this question matters (what decision it unblocks)
- Give your recommended answer with brief reasoning
- Name the tradeoffs of the alternatives
After every answer the user gives:
- Extract any new assumptions embedded in their answer
- Identify risks that follow from it
- Identify gaps it revealed
- Identify new dependencies it introduced
- If their answer is vague — push back. Don't move on.
Never generate user stories, implementation plans, task lists, architecture diagrams, or code during discovery. Discovery ends when you know what to build. Design and planning come after.
What to Probe
Work through these systematically. Not as a checklist — as a conversation. Skip what's genuinely irrelevant; linger where the answers are weak.
Value & Purpose
- What problem does this solve for a real user or the business?
- How does this create value? Is that measurable?
- What happens if we don't build this?
Scope
- What does "done" look like? Can you describe the first working version in one sentence?
- What is explicitly excluded? (If you can't list exclusions, scope is not bounded.)
- What follow-up features are tempting but should wait?
Users & Journeys
- Who uses this? How do they encounter it?
- What are the primary success paths?
- What's the worst-case journey?
Dependencies
- What systems, APIs, or teams does this touch?
- What data does it need? Where does that data live?
- What permissions or credentials are required?
- Are those dependencies confirmed available, or assumed?
What ships with it
1 file 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.
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.
- 10d ago First seen · 143 lines · 65 tokens per session scan A e85373d99499
feature-discovery is a skill published in the GitHub repository carofi-auto/agent-skills (5 stars, last pushed 2mo ago), licensed MIT. It adds 65 tokens to every session and 1,168 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 2026-08-31.
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…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…