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/mayank-io/mstack/next-ideanpx skills add mayank-io/mstack --skill next-ideagit clone --depth 1 https://github.com/mayank-io/mstackWhat 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 | $0.00088 | $0.01228 |
| Opus 5 | $0.00044 | $0.00614 |
| Sonnet 5 | $0.00018 | $0.00246 |
| Haiku 4.5 | $0.00009 | $0.00123 |
Grade A, and why
next-idea 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 2d 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 — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Next Idea
Identify the single highest-leverage addition the project could make right now. Not a list, not a roadmap — one idea, fully argued.
The Question
What's the single smartest and most radically innovative and accretive and useful and compelling addition you could make to the project at this point?
Procedure
- Ground yourself in the project. Before generating ideas, read enough of the repository to know what exists. At minimum: top-level
README.md, the directory structure, anyCLAUDE.md/ design docs, and the most recent commits (git log --oneline -20). If a dashboard or project plan exists (e.g.docs/dashboard.md), read it. Skim, don't deep-dive — you need shape, not detail. - Generate a wide candidate set, silently. Brainstorm 8–15 candidate additions internally. Do NOT show this list to the user. Cover different axes: new capability, new UX, new integration, new abstraction, new audience, new business model, new defensive moat, removing something, inverting an assumption.
- Score each candidate on four dimensions:
- Smart: non-obvious, leverages something unique about this project's position.
- Radically innovative: surprises a reader; not a "fast follow."
- Accretive: compounds with what already exists rather than replacing it.
- Useful & compelling: a real user (or self) would be visibly better off; the idea is easy to want.
- Pick the single winner. If two are close, pick the one with the larger blast radius if it works.
- Stress-test it. Spend a moment trying to kill the idea: what's the strongest objection, what would have to be true for it to fail, what's the cheapest experiment that would falsify it. Keep the answers — they go in the output.
- Write the output in the exact format below.
Output Format
Follow BLUF + Pyramid Principle strictly. Hierarchical numbering on every header. No prose before §1. No preamble like "Here's my analysis." Start at ## 1. Objective.
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.
- 2d ago First seen · 98 lines · 88 tokens per session scan A 6f7fa33a0eae
next-idea is a skill published in the GitHub repository mayank-io/mstack (5 stars, last pushed 8d ago), licensed MIT. It adds 88 tokens to every session and 1,228 once invoked, about $0.0004 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.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
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…
agent-host-chat-contributions
Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.