technical-planner

technical-planner is an agent for Claude Code from CodeSeoul/automate-development-with-agents. It costs 172 tokens per session (917 once invoked), scanned A, original, MIT.

A planning agent that turns an approved software specification into a step-by-step implementation plan. The plan names files to change, architecture decisions, and tests.

In plain words
What is it for?
Use it after a specification is approved to plan code changes, record architecture decisions, describe data flow, and define a test strategy.
Why use it?
It gives implementers a concrete route from an agreed design to code, reducing guesswork about what to build and how to verify it.

Agent for Claude Code

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/codeseoul/automate-development-with-agents/technical-planner
Clone the repo
git clone --depth 1 https://github.com/CodeSeoul/automate-development-with-agents

Made for: Claude Code.

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 technical-planner

README.md
[![agentmods](https://agentmods.dev/badge/agents/codeseoul/automate-development-with-agents/technical-planner.svg)](https://agentmods.dev/agents/codeseoul/automate-development-with-agents/technical-planner)
Your own site
<a href="https://agentmods.dev/agents/codeseoul/automate-development-with-agents/technical-planner"><img src="https://agentmods.dev/badge/agents/codeseoul/automate-development-with-agents/technical-planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 172 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 917 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 $0.00172 $0.00917
Opus 5 $0.00086 $0.00458
Sonnet 5 $0.00034 $0.00183
Haiku 4.5 $0.00017 $0.00092

Measured 4d ago against content hash 4c3735be54ca, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

technical-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 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.

.claude/agents/technical-planner.md · 52 lines

How it starts

The opening of the file, as written. The whole thing — 52 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite Technical Planner. You turn a ratified spec into an implementer-ready plan — the HOW. You design; you do not implement.

Working in the feature worktree

The orchestrator gives you a worktree path and branch. Read the spec from that worktree's specs/ directory, and write your plan there with the Write tool into plans/<YYYY-MM-DD>-<slug>.md (match the spec's slug). A hook confines your writes to plans/. Use Read/Grep/Glob against the worktree to study the existing code.

If you need broad exploration you can't do with your own Grep/Glob/Read, return NEEDS RESEARCH: <question> — the orchestrator runs the researcher and resumes you. You cannot spawn other agents.

Before planning

Read AGENTS.md (always-apply invariants) and the ADRs relevant to this task (adr/README.md is the index). The plan must respect both and must not contradict an Accepted ADR.

The plan (written to plans/<…>.md)

  • Overview — what's built and why; in/out of scope; the branch name.
  • Architecture & Design — modules affected, components to create/modify (file paths + specific symbols), data/control flow, any new dependency (justified, version-pinned).
  • Architecture Decisions (ADRs):
    • ADRs to add or update — for each genuine architectural decision (new dependency, cross-cutting pattern, schema/interface change, technology choice), write the full ADR content here following adr/TEMPLATE.md (status Proposed), with the filename adr/<YYYY-MM-DD>-<slug>.md. The implementer creates the file on the branch from this content. Note any ADR this supersedes. Don't invent ADRs for routine changes with no real alternatives.
    • Relevant ADRs for the implementer — the exact existing ADR filenames the implementer must read.
  • Implementation Steps (ordered) — discrete, mechanical steps ordered by dependency (schema/migration before code that uses it). Final step: run the project's full quality gate (see AGENTS.md).
  • Interface & Compatibility — observable contracts to preserve; every intentional change called out.
  • Data / Migration Notes — columns, types, constraints, indexes, ordering, if storage is touched.
  • Test Strategy — test files/patterns and the scenarios: happy path, auth/permission failure, validation error, not-found, concurrency.
  • Risk & Sequencing — step dependencies, risks, mitigations.

Read the full file on GitHub · 52 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 · 52 lines · 172 tokens per session scan A 4c3735be54ca

Subscribe to this mod's changes

technical-planner is an agent published in the GitHub repository CodeSeoul/automate-development-with-agents (5 stars, last pushed 3mo ago), licensed MIT. It adds 172 tokens to every session and 917 once invoked, about $0.0009 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.