Borrowing it
Nothing to install: this file belongs to AutomatosAI/automatos-ai. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AutomatosAI/automatos-ai/main/.claude/skills/prd-classify/SKILL.mdgit clone --depth 1 https://github.com/AutomatosAI/automatos-aiWrote 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/automatosai/automatos-ai/prd-classify)<a href="https://agentmods.dev/skills/automatosai/automatos-ai/prd-classify"><img src="https://agentmods.dev/badge/skills/automatosai/automatos-ai/prd-classify/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/automatosai/automatos-ai/prd-classify"><img src="https://agentmods.dev/badge/skills/automatosai/automatos-ai/prd-classify.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 | $0.00047 | $0.00907 |
| Opus 5.5 | $0.00019 | $0.00363 |
| Sonnet 5.5 | $0.00009 | $0.00181 |
| Haiku 4.5 | $0.00005 | $0.00091 |
Grade A, and why
prd-classify 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 1mo 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 — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Classifier
Slash command: /prd-classify <PRD#> or /prd-classify (then paste the PRD).
This skill enforces CLAUDE.md §3 ("REUSE over BUILD"). It surfaces existing surfaces in the codebase before estimating, so a PRD doesn't get costed as net-new when it's actually a relabel.
Workflow
1. Read the PRD
Locate the PRD file in docs/PRDs/ or wherever the user dropped it. Read it end-to-end. Note:
- The stated goal
- The user-facing artifacts mentioned (pages, components, tables, tools, agents)
- Any "build / create / add" language
2. Map existing surfaces (mandatory)
For each artifact mentioned in the PRD, check what already exists. Use parallel searches:
- Frontend components:
grep -rli "<artifact>" frontend/components/ - Hooks:
find frontend/hooks -type f | xargs grep -li "<artifact>" - API routers:
grep -rl "@router\." orchestrator/api/ | xargs grep -l "<artifact>" - DB tables:
grep -rE "class \w+\(.*Base" orchestrator/modules/ orchestrator/core/ | grep -i "<artifact>" - Platform tools: read
orchestrator/core/platform/platform_actions.py - Skills:
ls ../automatos-skills/ - Knowledge graph: query
graphify-out/graph.json(if present) for related nodes
If any of these already exist, list them with paths before proceeding.
3. Classify
Pick exactly one classification:
| Type | Signal | Default action |
|---|---|---|
| Rehouse / IA change | "Move X from Y to Z", "rename", "redesign page" | Components/hooks/APIs exist. Move/relabel, don't rebuild. |
| Refactor / Consolidation | "Unify X and Y", "deprecate", "single source of truth" | Pick canonical path, migrate others, delete the losers. |
| Extension | "Add X to existing Y" | New code is the increment, not the system. |
| Net-new feature | No precedent in the platform | Justify why it doesn't fit an existing pattern. |
4. Surface ambiguity
If anything is unclear, ask before estimating. Examples:
- "PRD says 'build the Reports page' — I see
frontend/components/activity/activity-reports.tsx. Is the PRD adding to it or replacing it?" - "There are 3 things called
task_*in the schema. Which one does this touch?" - "The PRD reads like a config dial — should this be a setting, not a new code path?"
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.
- 1mo ago First seen · 81 lines · 47 tokens per session scan A efa8781956fc
prd-classify is a skill published in the GitHub repository AutomatosAI/automatos-ai (74 stars, last pushed today), licensed Apache-2.0. It adds 47 tokens to every session and 907 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-08-30.
Other skills, from other repositories
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
rag-pipeline
A guide to RAG, a method where a system retrieves relevant passages from an external knowledge base before an AI model writes an answer. It covers splitting documents, searching by meaning or exact words, combining results, and measuring retrieval quality.
setup-open-index
Install and configure Open Index as the read/write context layer for a domain-specialized agent. Use when setting up a legal, marketing, customer support, sales, infrastructure, or other domain agent with Open Index over MCP.
remake-deck
Remake a company's source pitch deck (PDF, PPTX, or folder of slide images) into N clean-room design variants that play in the DidiDecks Scroll-UI shell. The agent takes the VP Eng / orchestrator role and runs the dididecks-ai plan Remake-Source-Deck-into-Design-Variants, which extracts and audits the deck, fans out N…
go4
Use when designing, architecting, planning, or debugging any system with an LLM in it — agents, agent loops, RAG and retrieval, prompt pipelines, multi-agent or subagent orchestration, tool use and MCP, memory and context management, evals, or production guardrails. Trigger BEFORE committing to an approach — choosing…
rag-pipelines
Best practices for Retrieval-Augmented Generation (RAG) pipelines. Use when working with vector databases, embeddings, chunking strategies, semantic search, or hybrid search architectures.