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/funkyoz/funkyoz-plugins/plangit clone --depth 1 https://github.com/FunkyOz/funkyoz-pluginsWhat 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 | $0.00013 | $0.01083 |
| Opus 5 | $0.00006 | $0.00541 |
| Sonnet 5 | $0.00003 | $0.00217 |
| Haiku 4.5 | $0.00001 | $0.00108 |
Grade A, and why
plan 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 yesterday.
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 — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Plan Feature Command
You are a senior software engineer tasked with breaking down a feature request into well-structured, actionable tasks.
Input
The user wants to implement: {{1}}
Process
Step 1: Analyze the Project
First, analyze the current project to understand:
- Technology stack - What languages, frameworks, and tools are used?
- Project structure - How is the code organized?
- Existing patterns - What design patterns, coding conventions, and practices are already in use?
- Dependencies - What external libraries or services are used?
If this is an empty or new project:
- Ask the user about their preferred technology stack
- Recommend best practices for their chosen stack
- Suggest a clean, maintainable project structure
Step 2: Break Down the Feature
Decompose the feature into logical tasks following these principles:
- Single Responsibility - Each task should have one clear objective
- Proper Sequencing - Tasks should be ordered by dependencies
- Appropriate Granularity - Not too large (hard to track), not too small (overhead)
- Testable Outcomes - Each task should have verifiable acceptance criteria
Step 3: Organize into Phases
Group related tasks into phases:
- Foundation - Setup, configuration, base infrastructure
- Core Implementation - Main functionality
- Advanced Features - Optional enhancements
- Testing - Unit tests, integration tests
- Documentation - README, examples, API docs
Step 4: Create Task Files
Create a tasks/ directory in the project root with the following structure:
00-index.md
Create the main index file following this template:
# [Feature Name] - Task Index
This directory contains all implementation tasks for [feature description].
## Overview
**Total Tasks:** [count]
**Estimated Timeline:** [estimate]
**Current Status:** Planning Phase
---
## Phase N: [Phase Name] ([Priority] Priority)
[Phase description]
| # | Task | Priority | Complexity | Status | Dependencies |
|---|------|----------|------------|--------|--------------|
| XX | [Task Name](XX-task-slug.md) | [Priority] | [Complexity] | `todo` | [Deps] |
**Phase Duration:** [estimate]
**Deliverables:** [list]
---
[Repeat for each phase]
## Quick Reference
### Critical Path
[List minimum tasks for MVP]
### Task Status Legend
- `todo` - Not started
- `progress` - Currently being worked on
- `done` - Completed and tested
### Complexity Ratings
- **Low** - Straightforward implementation, ~1-2 days
- **Medium** - Moderate complexity, ~3-5 days
- **High** - Complex implementation, ~1-2 weeks
---
**Last Updated:** [date]
**Document Version:** 1.0
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.
- yesterday First seen · 160 lines · 13 tokens per session scan A 5706b48453c0
plan is a command published in the GitHub repository FunkyOz/funkyoz-plugins (2 stars, last pushed 8mo ago), licensed MIT. It adds 13 tokens to every session and 1,083 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 commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.
implement
Execute the implementation plan by processing and executing all tasks defined in tasks.md.