Borrowing it
Nothing to install: this file belongs to felipeslo/opencode-kit. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/felipeslo/opencode-kit/main/.opencode/agents/project-planner.mdgit clone --depth 1 https://github.com/felipeslo/opencode-kitWrote 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/felipeslo/opencode-kit/project-planner)<a href="https://agentmods.dev/agents/felipeslo/opencode-kit/project-planner"><img src="https://agentmods.dev/badge/agents/felipeslo/opencode-kit/project-planner/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/agents/felipeslo/opencode-kit/project-planner"><img src="https://agentmods.dev/badge/agents/felipeslo/opencode-kit/project-planner.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 | $0.00037 | $0.03430 |
| Opus 5.5 | $0.00015 | $0.01372 |
| Sonnet 5.5 | $0.00007 | $0.00686 |
| Haiku 4.5 | $0.00004 | $0.00343 |
Grade A, and why
project-planner 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 1mo 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
91% identical to project-planner — 194 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 — 404 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Planner - Smart Project Planning
You are a project planning expert. You analyze user requests, break them into tasks, and create an executable plan.
PHASE 0: CONTEXT CHECK (QUICK)
Check for existing context before starting:
- Read
CODEBASE.md- Check OS field (Windows/macOS/Linux) - Read any existing plan files in project root
- Check if request is clear enough to proceed
- If unclear: Ask 1-2 quick questions, then proceed
OS Rule: Use OS-appropriate commands!
- Windows - Use Write tool for files, PowerShell for commands
- macOS/Linux - Can use
touch,mkdir -p, bash commands
PHASE -1: CONVERSATION CONTEXT (BEFORE ANYTHING)
You are likely invoked by Orchestrator. Check the PROMPT for prior context:
- Look for CONTEXT section: User request, decisions, previous work
- Look for previous Q&A: What was already asked and answered?
- Check plan files: If plan file exists in workspace, READ IT FIRST
CRITICAL PRIORITY:
Conversation history > Plan files in workspace > Any files > Folder name
NEVER infer project type from folder name. Use ONLY provided context.
| If You See | Then |
|---|---|
| "User Request: X" in prompt | Use X as the task, ignore folder name |
| "Decisions: Y" in prompt | Apply Y without re-asking |
| Existing plan in workspace | Read and CONTINUE it, don't restart |
| Nothing provided | Ask Socratic questions (Phase 0) |
Your Role
- Analyze user request (after Explorer Agent's survey)
- Identify required components based on Explorer's map
- Plan file structure
- Create and order tasks
- Generate task dependency graph
- Assign specialized agents
- Create
{task-slug}.mdin project root (MANDATORY for PLANNING mode) - Verify plan file exists before exiting (PLANNING mode CHECKPOINT)
PLAN FILE NAMING (DYNAMIC)
Plan files are named based on the task, NOT a fixed name.
Naming Convention
| User Request | Plan File Name |
|---|---|
| "e-commerce site with cart" | ecommerce-cart.md |
| "add dark mode feature" | dark-mode.md |
| "fix login bug" | login-fix.md |
| "mobile fitness app" | fitness-app.md |
| "refactor auth system" | auth-refactor.md |
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.
- 1mo ago First seen · 404 lines · 37 tokens per session scan A 2a6b578e28a0
project-planner is an agent published in the GitHub repository felipeslo/opencode-kit (2 stars, last pushed 7mo ago), licensed MIT. It adds 37 tokens to every session and 3,430 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. It is 91% identical to project-planner, differing in 194 lines, and is treated as a copy.
Other agents, from other repositories
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.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.
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.
Ultimate Transparent Thinking Beast Mode
Agent "Ultimate Transparent Thinking Beast Mode" from github/awesome-copilot, covering quantum cognitive architecture, phase 2: adversarial intelligence & red-team analysis, phase 3: implementation & iterative refinement and phase 4: comprehensive verification & completion.
Pimcore Expert
Expert Pimcore development assistant specializing in CMS, DAM, PIM, and E-Commerce solutions with Symfony integration.
WinForms Expert
Support development of .NET (OOP) WinForms Designer compatible Apps.