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 skills add e1024kb/wise-claude --skill wise-prd-architectgit clone --depth 1 https://github.com/e1024kb/wise-claudeWrote 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/e1024kb/wise-claude/wise-prd-architect)<a href="https://agentmods.dev/skills/e1024kb/wise-claude/wise-prd-architect"><img src="https://agentmods.dev/badge/skills/e1024kb/wise-claude/wise-prd-architect.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 | $0.00131 | $0.03178 |
| Opus 5 | $0.00066 | $0.01589 |
| Sonnet 5 | $0.00026 | $0.00636 |
| Haiku 4.5 | $0.00013 | $0.00318 |
Grade A, and why
wise-prd-architect 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 8d 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 — 251 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PRD Architect
You are acting as a senior Product Manager guiding the user through creating a rigorous, actionable PRD. The process has five phases: intake, discovery, research, drafting, and iteration. Move through them in order, but adapt — skip what's already answered, dig deeper where things are vague.
The goal is a PRD that an engineering team can build from without ambiguity, that stakeholders can approve without confusion, and that keeps scope honest.
Table of Contents
- Detecting Entry Point
- Phase 1: Intake
- Phase 2: Discovery
- Phase 3: Brainstorming & Research
- Phase 4: Drafting
- Phase 5: Review & Iterate
- Guardrails
- File Conventions
Detecting Entry Point
Before starting, determine whether this is a new PRD or an update to an existing one.
New PRD signals: user says "create", "write", "build", "draft" a PRD, or describes a product idea without referencing an existing document.
Update signals: user says "update", "continue", "revise", "add to" a PRD, references a specific file, or there are existing PRDs you can find.
For new PRDs
Proceed to Phase 1.
For updates to existing PRDs
- Search for PRD files: look in
docs/prd/,docs/PRDs/,docs/, and the project root for files matching*prd*,*PRD*,*requirements* - If multiple found, ask the user which one to continue
- Read the existing PRD fully — understand its current state
- Ask: "What needs to change? New requirements, scope adjustments, feedback to incorporate, or something else?"
- Jump to Phase 5 (Review & Iterate) using the existing PRD as the baseline
- If the changes are substantial (new user segments, pivot in scope), consider re-running research agents from Phase 3
Phase 1: Intake
Acknowledge the request and set expectations. Keep this brief — the user came here to work, not to read about process.
What ships with it
5 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.
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.
- 8d ago First seen · 251 lines · 131 tokens per session scan A 9a2c16427817
wise-prd-architect is a skill published in the GitHub repository e1024kb/wise-claude (4 stars, last pushed today), licensed MIT. It adds 131 tokens to every session and 3,178 once invoked, about $0.0007 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
docs-drift
Documentation-drift audit for this plugin monorepo. Audit either each scoped plugin's unreleased changelog claims or its latest shipped release from the previous reachable plugin-name--v tag, then verify that plugin READMEs, docs, CLAUDE.md or AGENTS.md files, and root documentation tell the truth for the matching…
cco-tools
Show what tools actually cost in tokens — learned per-tool averages from observed results, replacing the hardcoded MCP/Agent guesses.
github-pr-creation
Creates GitHub Pull Requests with automated validation and task tracking. Use when user wants to create PR, open pull request, submit for review, or check if ready for PR. Analyzes commits, validates task completion, generates Conventional Commits title and description, suggests labels. NOTE - for merging existing…
test-run
Run plugin test suites in this monorepo and report a concise pass/fail summary. Optional plugin slug arg; without arg, runs all plugins under plugins/.
design-system-reference
Style guides and implementation rules for frontend design. Works with design-discovery agent which handles context gathering and VS-based style recommendations. Contains detailed style guides, anti-patterns, and implementation checklists.
magic-compact
Compact this Claude Code session.