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/prdnpx skills add ashtonian/llm-init --skill prdgit 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/prd)<a href="https://agentmods.dev/skills/ashtonian/llm-init/prd"><img src="https://agentmods.dev/badge/skills/ashtonian/llm-init/prd.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 | $0.00012 | $0.00972 |
| Opus 5 | $0.00006 | $0.00486 |
| Sonnet 5 | $0.00002 | $0.00194 |
| Haiku 4.5 | $0.00001 | $0.00097 |
Grade A, and why
prd 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 3d 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 — 108 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Interactive PRD-to-tasks pipeline. Generate a Product Requirements Document from a feature description, then convert it into sized task files for agent team execution.
Instructions
Work through 3 phases. Present options with lettered choices (A, B, C, D) for quick user responses.
Phase 1: Interactive Discovery
Conduct a focused Q&A to understand the feature. Ask 2-3 questions per round, max 4 rounds.
Round 1 -- Scope & Users
- Who is this for? (A) Internal team, B) End users, C) API consumers, D) All)
- What problem does it solve? (open-ended, 1-2 sentences)
- What's the MVP scope? (A) Minimal -- one happy path, B) Standard -- happy path + errors, C) Full -- complete feature)
Round 2 -- Technical Shape
- Primary interaction pattern? (A) REST API, B) GraphQL, C) CLI, D) UI form, E) Background job)
- Data storage needs? (A) New table/model, B) Extend existing model, C) No persistence, D) External service)
- Auth requirements? (A) None/public, B) Authenticated only, C) Role-based, D) Custom)
Round 3 -- Dependencies & Constraints (if needed)
- External dependencies? (APIs, services, libraries)
- Performance constraints? (latency, throughput, data volume)
- Any existing code to build on?
Round 4 -- Edge Cases (if needed)
- Error handling strategy? (A) Return errors to caller, B) Retry + fallback, C) Queue for later, D) Depends on case)
- Concurrency concerns? (A) Single-user, B) Multi-user but no conflicts, C) Needs locking/transactions)
Adapt questions based on previous answers. Skip rounds that aren't relevant.
Phase 2: Generate PRD
After the Q&A, generate a structured PRD document:
# PRD: {Feature Name}
## Summary
{2-3 sentence description}
## User Stories
- As a {role}, I want {action} so that {benefit}
- ...
## Acceptance Criteria
- [ ] {Criterion with specific, testable condition}
- ...
## Technical Approach
- {Architecture decisions from the Q&A}
- {Data model changes}
- {API contracts}
## Out of Scope
- {What this does NOT include}
## Priority Order
1. {Data layer / models}
2. {Business logic / services}
3. {API / UI layer}
4. {Integration / E2E tests}
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.
- 3d ago First seen · 108 lines · 12 tokens per session scan A c7a318b0d99b
prd is a skill published in the GitHub repository ashtonian/llm-init (2 stars, last pushed 6mo ago), licensed MIT. It adds 12 tokens to every session and 972 once invoked, about $0.0001 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.
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.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
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…