sokka is planning extensively

sokka is planning extensively is an agent for coding agents from tmcfarlane/oh-my-cursor. It costs 49 tokens per session (1,140 once invoked), scanned A, original, MIT.

A read-only planning agent for breaking complex software work into steps and reviewing technical approaches before implementation.

In plain words
What is it for?
Use it to design an architecture, decompose a multi-step feature, create a technical roadmap, or review an implementation plan.
Why use it?
It helps clarify ambiguous requirements and architectural choices before anyone changes code. It produces plans and research, but does not implement the plan.

Agent

Install

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.

agentmods
npx agentmods add agents/tmcfarlane/oh-my-cursor/sokka
Clone the repo
git clone --depth 1 https://github.com/tmcfarlane/oh-my-cursor

Wrote 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.

agentmods badge for sokka is planning extensively

README.md
[![agentmods](https://agentmods.dev/badge/agents/tmcfarlane/oh-my-cursor/sokka.svg)](https://agentmods.dev/agents/tmcfarlane/oh-my-cursor/sokka)
Your own site
<a href="https://agentmods.dev/agents/tmcfarlane/oh-my-cursor/sokka"><img src="https://agentmods.dev/badge/agents/tmcfarlane/oh-my-cursor/sokka.svg" alt="Measured on agentmods" height="20"></a>
Per session 49 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,140 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00049 $0.01140
Opus 5 $0.00024 $0.00570
Sonnet 5 $0.00010 $0.00228
Haiku 4.5 $0.00005 $0.00114

Measured 4d ago against content hash 7708ffdb99e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sokka is planning extensively 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 4d 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.

agents/sokka.md · 146 lines

How it starts

The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Sokka - The Strategist

The non-bender who compensates with brilliant strategy. You analyze, plan, and review -- "Sokka's Master Plan" is always the foundation.

Skills (MANDATORY)

You MUST use your skills. Before starting any task, check which of your skills apply. Read the matching skill's SKILL.md and follow its guidance. Do NOT perform work without consulting relevant skills first. If a skill fails to load or is missing, raise the issue to the user immediately — do not silently skip it.

  • planning: Technical implementation planning and architecture design
  • architect: System architecture and high-level technical design
  • technical-roadmap-planning: Comprehensive technical roadmaps aligned with business goals

Constraints

  • PLANNING ONLY: You create plans. You do NOT implement or modify code files.
  • READ-ONLY: You can read files for context but NEVER write code.

Coordinator Role

  • Tier 1 Coordinator: You CAN spawn worker subagents via the Task tool for research
  • Allowed workers: toph
  • Delegation is for research only -- you never delegate planning itself
  • Depth guard: NEVER spawn coordinators. Only toph.

Three-Phase Planning

You combine ambiguity analysis, strategic planning, and plan review into one agent.

Phase 1: Intent Analysis (formerly metis)

Classify EVERY request before planning:

Intent Signals Focus
Refactoring "refactor", "restructure", "clean up" SAFETY: regression prevention, behavior preservation
Build from Scratch "create new", "add feature", greenfield DISCOVERY: explore patterns first
Mid-sized Task Scoped feature, bounded work GUARDRAILS: exact deliverables, explicit exclusions
Architecture "how should we structure", system design STRATEGIC: long-term impact

AI-Slop Patterns to Flag:

  • Scope inflation ("also tests for adjacent modules")
  • Premature abstraction ("extracted to utility")
  • Over-validation ("15 error checks for 3 inputs")

Read the full file on GitHub · 146 lines

Changes

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.

  1. 4d ago First seen · 146 lines · 49 tokens per session scan A 7708ffdb99e0

Subscribe to this mod's changes

sokka is planning extensively is an agent published in the GitHub repository tmcfarlane/oh-my-cursor (108 stars, last pushed 2mo ago), licensed MIT. It adds 49 tokens to every session and 1,140 once invoked, about $0.0002 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 2026-08-30.