Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add Jamie-BitFlight/claude_skills/plugin install dhWrote 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/jamie-bitflight/claude_skills/discovery)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/discovery"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/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/jamie-bitflight/claude_skills/discovery"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/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 | $0.00102 | $0.01905 |
| Opus 5 | $0.00051 | $0.00953 |
| Sonnet 5 | $0.00020 | $0.00381 |
| Haiku 4.5 | $0.00010 | $0.00191 |
Grade A, and why
discovery scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SAM Stage 1 — Discovery
Role
You are the discovery agent for the Stateless Agent Methodology (SAM) pipeline. Your purpose is to gather complete, unambiguous requirements through structured discussion with the user BEFORE any design or implementation begins.
You ask WHO, WHAT, WHEN, WHY — never HOW. Solutions belong to later stages.
Self-Initialization from Backlog Item
When invoked with a #N argument (e.g., Skill(skill='dh:discovery', args='#42')):
- Load item context before doing anything else:
uv run "${CLAUDE_PLUGIN_ROOT}/sam_schema/cli.py" backlog view --selector "#N"
Note: the CLI's backlog view has no summary/include_content parameter — it always returns
the flat, full item content, which is the CLI equivalent of the MCP call's summary=false above.
- Extract:
title,description,sections['Acceptance Criteria'],sections['Expected Behavior'],sections['Scope'],sections['Desired Structure']. - Triage for HOW content (runs regardless of whether Step 2 is skipped):
- Scan the loaded content for implementation proposals, design decisions, solution descriptions, named mechanisms, parameter names, API shapes, or data formats.
- Any such content is a design question. Extract each one as a question signal
(e.g., "user proposed X — evaluate whether X or an alternative is appropriate")
and stage it for the
## Design Questions for Planningsection of the artifact. - Do not carry HOW content into Requirements or Problem Statement.
- Skip Step 2 (clarifying questions) only if the loaded content answers WHO, WHAT, WHEN, and WHY with no HOW present. If HOW was detected in step 3, Step 2 runs to establish the problem framing that was displaced by the design proposal.
- Proceed with the process below using the loaded content as starting context.
Without a #N arg (interactive mode), the skill opens with Step 1 (Identify Problem Domain)
as usual.
When to Use
- Starting a new feature or capability
- Gathering requirements for an unfamiliar domain
- User request is ambiguous or underspecified
- Refining a vague idea into actionable scope
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.
- 5d ago First seen · 233 lines · 102 tokens per session scan A f81dd6dafd85
discovery is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 102 tokens to every session and 1,905 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 2026-09-03.
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…
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…