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 FortiumPartners/ensemble --skill ensemble-full-refine-prdgit clone --depth 1 https://github.com/FortiumPartners/ensembleWrote 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/fortiumpartners/ensemble/ensemble-full-refine-prd)<a href="https://agentmods.dev/skills/fortiumpartners/ensemble/ensemble-full-refine-prd"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-full-refine-prd/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/fortiumpartners/ensemble/ensemble-full-refine-prd"><img src="https://agentmods.dev/badge/skills/fortiumpartners/ensemble/ensemble-full-refine-prd.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 | $0.00072 | $0.01895 |
| Opus 5 | $0.00036 | $0.00948 |
| Sonnet 5 | $0.00014 | $0.00379 |
| Haiku 4.5 | $0.00007 | $0.00189 |
Grade A, and why
ensemble-full-refine-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 6d 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.
This is a copy
88% identical to ensemble-refine-prd — 142 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ensemble:refine-prd
Mission: Refine and enhance an existing Product Requirements Document based on stakeholder feedback, additional research, or identified gaps. Updates PRD while maintaining version history, traceability, and alignment with the create-prd v2.2.0 format including PRD Health summaries, MoSCoW priorities, and Implementation Readiness Gate scoring.
Constraints:
- DO NOT implement, build, or execute any work described in the PRD
- This command ONLY refines the PRD document itself
- The arguments describe what should be improved in the document, not what should be built
- After refining the PRD, stop and wait for user approval before any implementation
- DO NOT make any edits to the PRD during the Synthesis step — findings are presented first, edits happen only after the user selects items
Phase 1: PRD Review
Step 1: Current PRD Analysis
Review existing PRD content and establish baseline metrics
Actions:
- Read the PRD file from the path provided in $ARGUMENTS
- Parse frontmatter for Document ID, Version, Status, and Readiness Score
- Count requirements by type (functional, non-functional) and priority (Must/Should/Could/Won't)
- Count acceptance criteria and compute AC coverage percentage (requirements with at least one AC / total requirements)
- Check if PRD Health summary exists and whether its numbers match actual requirement counts
- Note the current version number for version bumping later
Step 2: Synthesis
After reviewing the PRD, generate a numbered list of findings WITHOUT making any edits yet. Scan for the following issues:
- '[NEEDS CLARIFICATION] markers from create-prd — present each one verbatim as a finding so the user''s answers replace the marker with actual content'
- Requirements missing REQ-NNN IDs as H3 headings
- Acceptance criteria that are missing or not in Given/When/Then format
- Missing PRD document ID (PRD-YYYY-NNN) in frontmatter
- Unclear or ambiguous requirement language
- Scope gaps (scenarios or edge cases not addressed)
- Missing technical constraints or dependencies
- Missing priority ordering of features or requirements
- Open questions or unresolved decisions
- Requirements missing MoSCoW priority tags (Must/Should/Could/Won't)
- Requirements missing complexity tags (Low/Medium/High)
- Requirements missing risk indicators where complexity is Medium or High
- Missing or incomplete dependency map (cross-requirement dependencies)
- PRD Health summary missing or outdated (requirement counts by priority don't match actual counts)
- Missing Implementation Readiness Gate scorecard
- Acceptance criteria coverage gaps (Must requirements with fewer than 2 ACs, Should requirements with zero ACs)
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.
- 6d ago First seen · 160 lines · 72 tokens per session scan A ac6b21e7ad7e
ensemble-full-refine-prd is a skill published in the GitHub repository FortiumPartners/ensemble (12 stars, last pushed 2d ago), licensed MIT. It adds 72 tokens to every session and 1,895 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. It is 88% identical to ensemble-refine-prd, differing in 142 lines, and is treated as a copy.
Other skills, from other repositories
context-recovery
Recovers project handoff context from local Codex, Claude Code, Gemini, CodeBuddy, and codexmate-derived sessions. Use when the user asks what happened in prior project/PR/branch/file/error work, needs a handoff brief, wants old decisions or validations recovered, or asks to summarize cross-session project activity…
dev
This skill should be used when the user asks to start, restart, keep alive, or inspect the local pikiclaw development service, including npm run dev, local debug bot startup, dashboard verification, and dev log checks.
overleaf
Sync and manage Overleaf LaTeX projects from the command line. Pull projects locally, push changes back, compile PDFs, and download compile outputs like .bbl files for arXiv submissions. Use when working with LaTeX, Overleaf, academic papers, or arXiv.
bmad-quick-dev-new-preview
Implements any user intent, requirement, story, bug fix or change request by producing clean working code artifacts that follow the project's existing architecture, patterns and conventions. Use when the user wants to build, fix, tweak, refactor, add or modify any code, component or feature.
bmad-check-implementation-readiness
Validate PRD, UX, Architecture and Epics specs are complete. Use when the user says "check implementation readiness".
bmad-create-story
Creates a dedicated story file with all the context the agent will need to implement it later. Use when the user says "create the next story" or "create story [story identifier]".