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/arch3rpro/ark-space/prd-createnpx skills add arch3rPro/ark-space --skill prd-creategit clone --depth 1 https://github.com/arch3rPro/ark-spaceWhat 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 | $0.00068 | $0.00720 |
| Opus 5 | $0.00034 | $0.00360 |
| Sonnet 5 | $0.00014 | $0.00144 |
| Haiku 4.5 | $0.00007 | $0.00072 |
Grade A, and why
prd-create 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 — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Create
Keep the standard PRD document structure. Preserve every functional-page field and its restriction: field name, control/type, required state, default value, format, range, validation, linkage, editability, visibility, permission, and persistence rule when applicable. Simplify only redundant workflow prose; do not mistake product fields for PRD template fields.
Default PRD Format
- Start from
assets/prd-template.md; retain its standard PRD sections. - In each Solution module, use the screenshot-first form in
assets/module-workflow-template.md. - Put a screenshot under a short screen or scenario heading.
- Put
需求描述immediately below the screenshot. - For a screen with functional fields, put its
页面字段与限制table directly below the description. Preserve all known field rules in that table. - Add branch flows, interaction constraints, page flows, data writes, error recovery, or technical contracts only when the screenshot, requirement description, and field table cannot express behavior R&D needs to implement.
- Mark an unknown as
待确认; never invent behavior or omit a known field restriction.
One screenshot may support several clear requirements. Do not require a screenshot for every click. Use relative image paths and short alt text. When screenshots are design references rather than executable product evidence, describe their behavior as requirements, not observed facts.
Page Field Rules
- Treat a page field as any input, selector, switch, upload, displayed value, editable item, or generated field that affects behavior or data.
- Keep its validation and restriction with the field: required/default, length or range, allowed format/value, uniqueness, dependency, editability, visibility, permission, save timing, and error message when known.
- Write
不适用only for a restriction that genuinely does not apply. Do not use it to hide an unknown; use待确认instead. - Do not duplicate field rules in branch/flow sections. Reference the field table when a later workflow section depends on it.
What ships with it
10 files 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.
- assets/decision-checklist-template.md 838 B
- assets/module-workflow-template.md 1.8 KB
- assets/prd-execution-checklist.md 5.5 KB
- assets/prd-template.md 2.0 KB
- references/evidence-levels.md 2.2 KB
- references/prd-rnd-workflow.md 12 KB
- scripts/audit-prd-portability.js 2.5 KB runs code
- scripts/package-prd.js 2.1 KB runs code
- scripts/validate-prd-images.js 1.3 KB runs code
- scripts/verify-prd-gates.js 11 KB runs code
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 · 46 lines · 68 tokens per session scan A 2051dc87c807
prd-create is a skill published in the GitHub repository arch3rPro/ark-space (2 stars, last pushed 7d ago), licensed MIT. It adds 68 tokens to every session and 720 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 2026-08-31.
Other skills, from other repositories
skill-authoring
Author SKILL.md skills: frontmatter, validator limits, structure.
obsidian-wiki-system
Initialize or maintain a reusable Obsidian wiki knowledge iteration system with raw inbox, wiki pages, source/concept/synthesis/project templates, workflows, prompts, indexes, logs, and AGENTS.md rules. Use in Codex, OpenCode, or any agent that can read skill folders when the user wants to create a new Obsidian vault…
agent-platform-model-registry
Agent Platform Model Registry Management. Use when you need to upload, list, describe, update, or delete machine learning models (and their versions) in the Agent Platform Model Registry. Don't use for model training, model deployment to endpoints, or managing non-Agent Platform models.
bigquery-ai-ml
Leverages BigQuery's built-in machine learning and GenAI capabilities for advanced data analytics. Use when you need to write SQL queries that perform time-series forecasting, predict values, detect outliers or anomalies, find key drivers, perform semantic search or vector search, classify text, calculate similarity…
twitter-reader
Read Twitter/X for financial research using opencli (read-only). Use this skill whenever the user wants to read their Twitter feed, search for financial tweets, view bookmarks, look up user profiles, or gather market sentiment from Twitter/X. Triggers include: "check my feed", "search Twitter for", "show my…
referral-program
When the user wants to design, launch, or optimize an in-app referral / invite / share-to-earn program — including reward structure, mechanics, fraud prevention, deep link setup, and viral coefficient measurement. Use when the user mentions "referral program", "invite a friend", "refer and earn", "share to earn"…