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/ashtonian/llm-init/requirementsnpx skills add ashtonian/llm-init --skill requirementsgit clone --depth 1 https://github.com/ashtonian/llm-initWrote 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/ashtonian/llm-init/requirements)<a href="https://agentmods.dev/skills/ashtonian/llm-init/requirements"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/requirements.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 | $0.00008 | $0.01180 |
| Opus 5 | $0.00004 | $0.00590 |
| Sonnet 5 | $0.00002 | $0.00236 |
| Haiku 4.5 | $0.00001 | $0.00118 |
Grade A, and why
requirements 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 — 150 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Gather requirements interactively to produce a package specification.
Instructions
You are entering an interactive requirements-gathering session. Your goal is to iteratively ask questions and make decisions with the user until you have enough information to produce a complete technical specification that can drive code generation.
Do NOT write code in this session. The output is a specification document only.
Phase 1: Discovery (Broad Questions)
Start by understanding the big picture. Ask about:
- What is the purpose of this package/feature? What problem does it solve?
- Who are the users/consumers? (API clients, other services, end users, CLI users)
- What are the key use cases? Walk through 2-3 primary scenarios.
- Are there existing systems this needs to integrate with?
- Any hard constraints? (performance, compatibility, regulatory, timeline)
Ask these one group at a time. Wait for answers before proceeding.
Phase 2: Scope & Boundaries
Narrow down the scope. Ask about:
- What is explicitly IN scope for v1? What's OUT of scope?
- What are the inputs and outputs for each use case?
- What data does this need to store or manage? What are the key entities?
- What external dependencies are needed? (databases, APIs, message queues)
- Non-functional requirements: latency, throughput, availability, data retention
Phase 3: Design Decisions
For each major design choice, present the user with 2-4 options including tradeoffs:
- Data storage: relational, document, in-memory, file-based, embedded
- API style: REST, gRPC, GraphQL, CLI, library/SDK
- Concurrency model: synchronous, async/await, event-driven, actor model
- Error handling: error codes, typed errors, result types, exceptions
- Authentication/authorization: JWT, OAuth2, API keys, mTLS, none
- Configuration: env vars, config files, flags, remote config
- Testing strategy: unit-heavy, integration-heavy, E2E-heavy, property-based
For each decision:
- Present available options with 1-sentence description
- Explain tradeoffs (what you gain vs. sacrifice)
- State your recommendation and why
- Ask the user to choose
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 · 150 lines · 8 tokens per session scan A 11147167da91
requirements is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 7mo ago), licensed MIT. It adds 8 tokens to every session and 1,180 once invoked, about $0.0000 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…
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…
chronicle
Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…