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 Jamie-BitFlight/claude_skills --skill what-nextgit clone --depth 1 https://github.com/Jamie-BitFlight/claude_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/jamie-bitflight/claude_skills/what-next)<a href="https://agentmods.dev/skills/jamie-bitflight/claude_skills/what-next"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/what-next/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/what-next"><img src="https://agentmods.dev/badge/skills/jamie-bitflight/claude_skills/what-next.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00066 | $0.02102 |
| Opus 5 | $0.00033 | $0.01051 |
| Sonnet 5 | $0.00013 | $0.00420 |
| Haiku 4.5 | $0.00007 | $0.00210 |
Grade A, and why
what-next 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 8d 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 — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
What Next
Use this skill to choose and execute the next move when the path is uncertain, trust is damaged, or the work needs more than the first plausible idea.
The core loop is:
reconstruct goal -> reverse prerequisites -> classify completeness -> discover before asking
-> generate approach options -> adversarially eliminate -> synthesize
-> execution gate -> delegate/implement -> validate real behavior -> record concerns -> repeat
Operating Rules
- Treat agreement, apology, and polished restatement as zero progress unless they produce an observable next action or decision.
- Generate multiple materially different approaches before choosing one. Five is a useful forcing function, not a required task count.
- Separate generation from evaluation. Do not critique options while brainstorming them.
- Use evidence before asking the user. If a question can be answered by reading source, docs, tests, runtime behavior, official documentation, or internet research, do that first.
- Use subagents for adversarial critique and independent work when available. If subagents are unavailable, perform the same critique directly and record that limitation as a validation or process concern.
- Do not execute implementation work until required execution inputs are available, evidence-derived, or safely defaulted.
- Validate through the actual mechanism the user depends on. Manual inspection can support diagnosis, but it is not proof of product behavior.
Step 1: Reconstruct The Goal
Write a compact goal frame before planning:
Goal:
- [One sentence describing the desired outcome]
Success output:
- [Observable artifact, behavior, test result, deployment state, or decision]
Scope:
- In scope: [known]
- Out of scope: [known]
Current evidence:
- [Facts already known, with sources when available]
Current risks:
- [Unproven assumptions, unknown changes, failed validations, or trust gaps]
If the goal cannot be stated as an observable result, classify that as an unresolved input and route it through discovery or a batched user question.
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.
- 8d ago First seen · 275 lines · 66 tokens per session scan A 4115f948822f
what-next is a skill published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 66 tokens to every session and 2,102 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…
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…