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 commands/yassinello/claude-plugin-prd-workflow/code-prdgit clone --depth 1 https://github.com/Yassinello/claude-plugin-prd-workflowWhat 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 | $0.01740 |
| Opus 5 | $0.00006 | $0.00870 |
| Sonnet 5 | $0.00002 | $0.00348 |
| Haiku 4.5 | $0.00001 | $0.00174 |
Grade A, and why
code-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 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 — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code PRD Command
Guided implementation using 4-phase Context Engineering workflow.
Purpose
Bridge PRD to implementation with:
- Context management: Never exceed 60% context for quality
- 4-Phase workflow: Research → Plan → Implement → Validate
- Persistent memory: Thoughts saved in
.prds/thoughts/ - Incremental progress: Clear checkpoints and validation
- Quality assurance: Continuous alignment with PRD
Workflow
Phase 1: Research (Context Gathering)
Goal: Deep codebase understanding before writing code.
Activities:
- Read PRD acceptance criteria and technical design
- Explore relevant codebase areas
- Identify existing patterns and conventions
- Find dependencies and integration points
- Note architectural constraints
- Document unknowns and questions
Output: Research summary saved in .prds/thoughts/research/PRD-XXX-research.md
Key questions:
- Where does this feature fit in the codebase?
- What patterns/conventions should I follow?
- What dependencies exist?
- What could go wrong?
Phase 2: Plan (Task Breakdown)
Goal: Detailed implementation plan with tasks and estimates.
Activities:
- Break down PRD into concrete tasks
- Identify task dependencies
- Estimate effort per task
- Plan testing strategy
- Define validation checkpoints
- Risk mitigation planning
Output: Implementation plan saved in .prds/thoughts/plans/PRD-XXX-plan.md
Plan structure:
- Task list with estimates
- Dependency graph
- Critical path identified
- Testing approach
- Validation criteria
Phase 3: Implement (Guided Development)
Goal: Execute plan incrementally with continuous validation.
Activities:
- Work task-by-task from plan
- Checkpoint after each major task
- Validate against acceptance criteria
- Adapt plan based on learnings
- Document decisions and trade-offs
- Keep context under 60%
Checkpoints:
- After each task: Does it work? Tests pass? Aligned with PRD?
- Before next task: Context cleanup if needed
- Major milestones: User validation opportunity
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 · 285 lines · 12 tokens per session scan A 7e02dea09726
code-prd is a command published in the GitHub repository Yassinello/claude-plugin-prd-workflow (12 stars, last pushed 9mo ago), licensed MIT. It adds 12 tokens to every session and 1,740 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 2026-08-30.
Other commands, from other repositories
backlog
The project layer: milestones, epics, and user stories with refusing controllers — spec-seeded, sprint-ready.
sprint
Scope-boxed sprints over the backlog: one active sprint, explicit carry-over, a close that refuses to hide unfinished work.
dashboard
CLI status display — terse one-screen view of plan tree, active task, conflicts, freezes, token budget, recent decisions.
resume_handoff
Resume work from handoff document with context analysis and validation.
create_handoff
Create handoff document for transferring work to another session.
plan-archive
Compress a completed branch. Alias for /aura-frog:plan archive (v3.7.2+).