~ / rigs / vshidlovsky / prd-agents-framework

vshidlovsky/prd-agents-framework

Multi-agent PRD framework for Claude Code — structured requirements creation and review using BABOK, perspective-based reading, and smell detection

↗ GitHub ★ 4 mit updated 2mo ago project Claude Code
share on X
ARCHETYPE
Orchestrator
A bench of specialised subagents. The main agent mostly delegates.
CONTEXT TAX · EVERY TURN
~402 tokens
Featherweight · median rig: 2.3k · breakdown
GUARDRAILS
0/5
No committed guardrails · details

Copy this rig

# review before running: this installs third-party code
$ npx degit vshidlovsky/prd-agents-framework/agents ./rig-prd-agents-framework/agents
$ npx degit vshidlovsky/prd-agents-framework/skills ./rig-prd-agents-framework/skills

MCP servers are added to Claude Code at local scope; env vars are shown as YOUR_… placeholders — we never store values. Files are fetched with degit into a separate folder so you can review before merging.

$ npx degit vshidlovsky/prd-agents-framework/skills/create-prd .claude/skills/create-prd
$ curl -fsSL --create-dirs -o .claude/agents/prd-reviewer.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/prd-reviewer.md
$ curl -fsSL --create-dirs -o .claude/agents/prd-senior-pm.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/prd-senior-pm.md
$ curl -fsSL --create-dirs -o .claude/agents/prd-smell-patterns.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/prd-smell-patterns.md
$ curl -fsSL --create-dirs -o .claude/agents/prd-writer.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/prd-writer.md
$ curl -fsSL --create-dirs -o .claude/agents/project-setup.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/project-setup.md
$ curl -fsSL --create-dirs -o .claude/agents/researcher.md https://raw.githubusercontent.com/vshidlovsky/prd-agents-framework/main/agents/researcher.md

This rig commits no guardrails. Here is the community baseline instead — the deny/ask rules most often found across all 6,974 rigs:

{
  "permissions": {
    "deny": [
      "Read(./.env)",
      "Read(**/.env)",
      "Read(~/.ssh/**)",
      "Bash(rm -rf *)",
      "Read(**/*.pem)",
      "Bash(rm -rf /)",
      "Bash(git push --force:*)",
      "Bash(sudo *)",
      "Read(~/.aws/**)",
      "Bash(rm -rf /*)",
      "Read(./.env.*)",
      "Read(.env)",
      "Bash(git push --force*)",
      "Bash(rm -rf:*)",
      "Read(**/.env.*)",
      "Read(**/*.key)",
      "Bash(sudo:*)",
      "Bash(git reset --hard*)",
      "Bash(git reset --hard:*)",
      "Read(.env.*)"
    ],
    "ask": [
      "Bash(git push:*)",
      "Bash(git push *)",
      "Bash(git commit:*)",
      "Bash(rm *)",
      "Bash(rm:*)",
      "Bash(npm publish:*)",
      "Bash(wget *)",
      "Bash(git rebase *)",
      "Bash(gh pr merge *)",
      "Bash(git commit *)"
    ]
  }
}

Skills (1)

Subagents (6)

prd-reviewer
model: opus
Reviews PRDs for completeness, API accuracy, and implementation readiness. Orchestrates parallel sub-reviewers with a three-phase matrix-driven process — scaffold, fill (parallel agents including a de
prd-senior-pm
model: fable
Judges a technical PRD review, decides the product questions it raises, and turns the survivors into revision tickets for the writer. Runs after prd-reviewer and before any revision cycle. Use when a
prd-smell-patterns—
prd-writer
model: opus
Drafts structured PRDs from plain-language initiative descriptions. Researches codebase and API docs, asks clarifying questions, writes a complete spec. Use when someone needs to create a new initiati
project-setup
model: opus
Detects project type, scans the repo, and drafts .claude/project-context.md automatically. Run once when adopting the PRD agents framework into a new project.
researcher
model: opus
Researches a codebase for a specific initiative. Traces code paths, extracts API contracts, documents business logic. Produces a structured research document. Use at the start of the PRD workflow.

Similar rigs

copied ✓