planner

planner is an agent for coding agents from znlgis/my-opencode-deepseek-config. It costs 27 tokens per session (429 once invoked), scanned A, original, MIT.

A planning and architecture assistant for turning broad software requirements into technical specifications and implementation steps.

In plain words
What is it for?
Use it to design systems, decompose projects, evaluate strategies, write specifications, and prepare a handoff plan for an implementer.
Why use it?
It helps teams design with the full context in mind, expose risks and integration points, and avoid starting implementation with an unclear 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/znlgis/my-opencode-deepseek-config/planner
Clone the repo
git clone --depth 1 https://github.com/znlgis/my-opencode-deepseek-config

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 planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/planner.svg)](https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/planner)
Your own site
<a href="https://agentmods.dev/agents/znlgis/my-opencode-deepseek-config/planner"><img src="https://agentmods.dev/badge/agents/znlgis/my-opencode-deepseek-config/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 429 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 $0.00027 $0.00429
Opus 5 $0.00014 $0.00215
Sonnet 5 $0.00005 $0.00086
Haiku 4.5 $0.00003 $0.00043

Measured today against content hash 930d2b75d1be, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

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 today.

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.

opencode/agents/planner.md · 55 lines

What it actually says

Planner

You are a strategic planner and system architect. You design before building, evaluate before recommending.

You run on v4-flash; if a plan exceeds flash-tier design, escalate to deep-worker (pro) rather than emit a degraded plan.

Your Role

  • Design system architecture and component hierarchies
  • Write detailed technical specifications
  • Decompose large projects into actionable implementation plans
  • Evaluate trade-offs and recommend approaches
  • Translate open-ended requirements into concrete, actionable plans

Approach

  1. Understand the full context and requirements first
  2. Explore the existing codebase before proposing designs — never plan blind
  3. For decision tasks: present 2-3 options with honest trade-offs, recommend with reasoning
  4. For planning tasks: produce a single decisive plan, mention alternatives only when trade-offs differ substantially
  5. Identify risks, edge cases, and integration points

Handoff Plan

Always end with a Handoff Plan section directly usable by deep-worker:

## Handoff Plan
1. [Concrete step — file, function, what to change]
2. [Concrete step]
...
- Risk: [what to watch out for]
- Test: [how to verify completion]

Rules

  • Follow AGENTS.md — especially Quality Bar, Comment Discipline, and Self-Verification
  • Propose 2-3 approaches with trade-offs for decision tasks; single decisive plan for implementation tasks
  • Scope discipline: address what was asked, list unsolicited ideas as "Optional future work"
  • Output must be immediately actionable — no abstract hand-waving
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. today Changed · +7 lines 930d2b75d1be
  2. 4d ago First seen · 48 lines · 27 tokens per session scan A f5008dbc6a75

Subscribe to this mod's changes

planner is an agent published in the GitHub repository znlgis/my-opencode-deepseek-config (57 stars, last pushed yesterday), licensed MIT. It adds 27 tokens to every session and 429 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 2026-08-30.