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/bia-technologies/yaxunitWrote 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/rules/bia-technologies/yaxunit/plan-mode-map)<a href="https://agentmods.dev/rules/bia-technologies/yaxunit/plan-mode-map"><img src="https://agentmods.dev/badge/rules/bia-technologies/yaxunit/plan-mode-map/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/rules/bia-technologies/yaxunit/plan-mode-map"><img src="https://agentmods.dev/badge/rules/bia-technologies/yaxunit/plan-mode-map.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 | $0.00000 | $0.02498 |
| Opus 5.5 | $0.00000 | $0.00999 |
| Sonnet 5.5 | $0.00000 | $0.00500 |
| Haiku 4.5 | $0.00000 | $0.00250 |
Grade A, and why
plan-mode-map 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.
Copies of this mod
4 near-identical copies found in the catalogue:
- plan-mode-map — 100% identical, 0 lines differ
- plan-mode-map — 100% identical, 0 lines differ
- plan-mode-map — 100% identical, 0 lines differ
- plan-mode-map — 94% identical, 6 lines differ
How it starts
The opening of the file, as written. The whole thing — 275 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PLAN MODE: TASK PLANNING PROCESS MAP
TL;DR: This visual map guides the PLAN mode process, focusing on creating detailed implementation plans based on the complexity level determined during initialization, with mandatory technology validation before implementation.
🧭 PLAN MODE PROCESS FLOW
graph TD
Start["START PLANNING"] --> ReadTasks["Read tasks.md<br>Core/task-tracking.md"]
%% Complexity Level Determination
ReadTasks --> CheckLevel{"Determine<br>Complexity Level"}
CheckLevel -->|"Level 2"| Level2["LEVEL 2 PLANNING<br>Level2/enhancement-planning.md"]
CheckLevel -->|"Level 3"| Level3["LEVEL 3 PLANNING<br>Level3/feature-planning.md"]
CheckLevel -->|"Level 4"| Level4["LEVEL 4 PLANNING<br>Level4/system-planning.md"]
%% Level 2 Planning
Level2 --> L2Review["Review Code<br>Structure"]
L2Review --> L2Document["Document<br>Planned Changes"]
L2Document --> L2Challenges["Identify<br>Challenges"]
L2Challenges --> L2Checklist["Create Task<br>Checklist"]
L2Checklist --> L2Update["Update tasks.md<br>with Plan"]
L2Update --> L2Tech["TECHNOLOGY<br>VALIDATION"]
L2Tech --> L2Verify["Verify Plan<br>Completeness"]
%% Level 3 Planning
Level3 --> L3Review["Review Codebase<br>Structure"]
L3Review --> L3Requirements["Document Detailed<br>Requirements"]
L3Requirements --> L3Components["Identify Affected<br>Components"]
L3Components --> L3Plan["Create Comprehensive<br>Implementation Plan"]
L3Plan --> L3Challenges["Document Challenges<br>& Solutions"]
L3Challenges --> L3Update["Update tasks.md<br>with Plan"]
L3Update --> L3Tech["TECHNOLOGY<br>VALIDATION"]
L3Tech --> L3Flag["Flag Components<br>Requiring Creative"]
L3Flag --> L3Verify["Verify Plan<br>Completeness"]
%% Level 4 Planning
Level4 --> L4Analysis["Codebase Structure<br>Analysis"]
L4Analysis --> L4Requirements["Document Comprehensive<br>Requirements"]
L4Requirements --> L4Diagrams["Create Architectural<br>Diagrams"]
L4Diagrams --> L4Subsystems["Identify Affected<br>Subsystems"]
L4Subsystems --> L4Dependencies["Document Dependencies<br>& Integration Points"]
L4Dependencies --> L4Plan["Create Phased<br>Implementation Plan"]
L4Plan --> L4Update["Update tasks.md<br>with Plan"]
L4Update --> L4Tech["TECHNOLOGY<br>VALIDATION"]
L4Tech --> L4Flag["Flag Components<br>Requiring Creative"]
L4Flag --> L4Verify["Verify Plan<br>Completeness"]
%% Technology Validation Gate - NEW
L2Tech & L3Tech & L4Tech --> TechGate["⛔ TECHNOLOGY<br>VALIDATION GATE"]
TechGate --> TechSelection["Document Technology<br>Stack Selection"]
TechSelection --> TechHelloWorld["Create Hello World<br>Proof of Concept"]
TechHelloWorld --> TechDependencies["Verify Required<br>Dependencies"]
TechDependencies --> TechConfig["Validate Build<br>Configuration"]
TechConfig --> TechBuild["Complete Test<br>Build"]
TechBuild --> TechVerify["⛔ TECHNOLOGY<br>CHECKPOINT"]
%% Verification & Completion
L2Verify & L3Verify & L4Verify & TechVerify --> CheckCreative{"Creative<br>Phases<br>Required?"}
%% Mode Transition
CheckCreative -->|"Yes"| RecCreative["NEXT MODE:<br>CREATIVE MODE"]
CheckCreative -->|"No"| RecImplement["NEXT MODE:<br>IMPLEMENT MODE"]
%% Style for Technology Gate
style TechGate fill:#ff5555,stroke:#dd3333,color:white,stroke-width:3px
style TechVerify fill:#ff5555,stroke:#dd3333,color:white,stroke-width:3px
style TechSelection fill:#4da6ff,stroke:#0066cc,color:white
style TechHelloWorld fill:#4da6ff,stroke:#0066cc,color:white
style TechDependencies fill:#4da6ff,stroke:#0066cc,color:white
style TechConfig fill:#4da6ff,stroke:#0066cc,color:white
style TechBuild fill:#4da6ff,stroke:#0066cc,color:white
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 · 275 lines · 0 tokens per session scan A 6315fff61b54
plan-mode-map is a cursor rule published in the GitHub repository bia-technologies/yaxunit (341 stars, last pushed 18d ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 2,498 tokens. 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 2026-09-01.
Other cursor rules, from other repositories
telegram-bot-tests
Test conventions for Telegram Bot library.
project-conventions
Core project conventions for the Uniqlo Sales Alerter.
testing
Testing conventions for Ion Design System using Jest and Angular Testing Library.
121-java-unit-testing
Java Unit testing guidelines.
use-contract-ir-factories
Use factory functions for creating ContractIR objects instead of manual object creation.
gonavi-go
A Go coding rule set for the GoNavi repository, based on common Go style guides and the project's own conventions. It covers file structure, errors, context, concurrency, logging, and tests.