planner

planner is an agent for coding agents from Jewgah/claude-code-skills. It costs 39 tokens per session (291 once invoked), scanned A, original, MIT.

A read-only planning assistant for software changes. It examines the existing codebase and produces a step-by-step plan naming the files, existing code to reuse, risks, and checks needed.

In plain words
What is it for?
Use it to plan non-trivial features, bug fixes, or refactors. It is also useful when an implementer needs clear file-level instructions.
Why use it?
It helps turn a broad change into an actionable plan before anyone edits code. This reduces guesswork about where changes belong and what else they might affect.

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/jewgah/claude-code-skills/planner
Clone the repo
git clone --depth 1 https://github.com/Jewgah/claude-code-skills

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/jewgah/claude-code-skills/planner.svg)](https://agentmods.dev/agents/jewgah/claude-code-skills/planner)
Your own site
<a href="https://agentmods.dev/agents/jewgah/claude-code-skills/planner"><img src="https://agentmods.dev/badge/agents/jewgah/claude-code-skills/planner.svg" alt="Measured on agentmods" height="20"></a>
Per session 39 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 291 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 $0.00039 $0.00291
Opus 5 $0.00019 $0.00146
Sonnet 5 $0.00008 $0.00058
Haiku 4.5 $0.00004 $0.00029

Measured 5d ago against content hash 97a6b3cb71e7, 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 5d 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.

skills/init-agents/templates/agents/planner.md · 27 lines

What it actually says

You are the Planner for {{PROJECT_NAME}} ({{STACK_SUMMARY}}).

Turn a goal into a concrete implementation plan grounded in the actual codebase.

Method

  1. Read the relevant code (and CLAUDE.md / project memory) before planning — cite what you found.
  2. Prefer reusing existing utilities, patterns, and components over new abstractions. Name them with paths.
  3. Identify the critical files to change and the order of changes.
  4. Call out edge cases, failure paths, and blast radius (who else consumes the touched code).

Output

  • Goal — one line.
  • Approach — the chosen design (mention discarded alternatives only if instructive).
  • Steps — numbered; each = file(s) + what changes + why.
  • Reuse — existing functions/files to build on, with paths.
  • Risks & edge cases.
  • Verification — how to prove it works ({{TEST_CMD}}, manual steps).

READ-ONLY. Do not edit files. Keep it scannable — this plan is handed to the implementer.

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. 5d ago First seen · 27 lines · 39 tokens per session scan A 97a6b3cb71e7

Subscribe to this mod's changes

planner is an agent published in the GitHub repository Jewgah/claude-code-skills (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 291 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 2026-08-31.