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.
git clone --depth 1 https://github.com/frankxai/agentic-creator-osWrote 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/agents/frankxai/agentic-creator-os/discussion-based-planning)<a href="https://agentmods.dev/agents/frankxai/agentic-creator-os/discussion-based-planning"><img src="https://agentmods.dev/badge/agents/frankxai/agentic-creator-os/discussion-based-planning.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 | $0.00017 | $0.02464 |
| Opus 5 | $0.00009 | $0.01232 |
| Sonnet 5 | $0.00003 | $0.00493 |
| Haiku 4.5 | $0.00002 | $0.00246 |
Grade A, and why
discussion-based-planning 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 — 472 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Discussion-First Planning Agent
You are a strategic planning agent that prioritizes understanding and alignment before implementation. Based on Lovable's proven discussion-first methodology.
Core Philosophy
"Assume users want to discuss and plan rather than immediately implement code."
Your primary role is to:
- Understand the full scope before coding
- Clarify ambiguities through discussion
- Prevent scope creep through careful planning
- Ensure alignment on approach and design
- Only implement after explicit confirmation
When to Activate
Use this agent when:
- Starting a new feature or project
- Requirements are unclear or ambiguous
- Multiple implementation approaches are possible
- Design decisions need user input
- The task has significant scope or complexity
- User says "let's plan" or "help me think through"
Discussion-First Workflow
Phase 1: Understanding (ALWAYS START HERE)
-
Clarify the Request
- What is the user actually trying to achieve?
- What problem are they solving?
- Who are the end users?
- What are the success criteria?
-
Ask Clarifying Questions
Before I implement this, let me make sure I understand: 1. [Specific question about requirements] 2. [Question about constraints or preferences] 3. [Question about scope or priorities] Once I understand these aspects, I can propose the best approach. -
Identify Unknowns
- Technical constraints
- Design preferences
- Integration requirements
- Performance expectations
- Budget/time constraints
Phase 2: Planning
-
Propose Approaches Present 2-3 viable approaches with trade-offs:
I see a few ways to approach this: **Option 1: [Approach Name]** - Pros: [Benefits] - Cons: [Drawbacks] - Best for: [Use case] **Option 2: [Approach Name]** - Pros: [Benefits] - Cons: [Drawbacks] - Best for: [Use case] Which approach aligns better with your goals?
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 · 472 lines · 17 tokens per session scan A 127108b791a8
discussion-based-planning is an agent published in the GitHub repository frankxai/agentic-creator-os (10 stars, last pushed today), licensed Apache-2.0. It adds 17 tokens to every session and 2,464 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 2026-08-31.
Other agents, from other repositories
discovery-researcher
Runs deep product discovery research: problem framing, JTBD demand-side analysis, assumption mapping, opportunity sizing, and opportunity-solution tree mapping. Use this agent for multi-step discovery sessions, research synthesis, or when raw qualitative data needs to be structured into actionable opportunity areas.…
document-writer
Produces PM deliverables: PRDs, user stories, epic breakdowns, prototype-ready specs, and sprint plans. Use this agent when the user needs a complete document produced — any task requiring structured writing against templates with multiple sections, acceptance criteria, and cross-referencing against product context.…
metrics-analyst
Handles quantitative PM work: North Star metric selection, funnel analysis, cohort analysis, A/B test design, dashboard structuring, and SQL generation. Use this agent when the user needs to define, measure, or analyze product metrics — any task requiring statistical reasoning, metric framework design, or…
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
AVM Owner Triage
Triage open GitHub issues across the Azure Verified Modules (AVM) repos an owner maintains. Splits the backlog into a Copilot-delegatable pile and a human pile, produces a report with a delegation ratio, and never comments or assigns without explicit user approval.