plan

plan is a skill for Claude Code from SyloRei/claude-godmode. It costs 48 tokens per session (3,381 once invoked), scanned A, original, MIT.

A command that turns a feature brief into an ordered implementation plan with dependencies and checks for every acceptance criterion. Dependencies show which steps must happen before others.

In plain words
What is it for?
Use it after writing a brief to break the work into executable steps, identify which steps can depend on or follow others, and define the verification plan.
Why use it?
It makes the build sequence explicit and exposes how completion will be checked before implementation begins.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: reads .claude/ paths.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the claude-godmode plugin — 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers shipped together

Good fit Use it after writing a brief to break the work into executable steps, identify which steps can depend on or follow others, and define the verification plan.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SyloRei/claude-godmode
Claude Code
/plugin install claude-godmode

Made for: Claude Code.

Or install claude-godmode, the plugin that ships this one along with the rest of its 14 skills, 4 commands, 19 agents, 7 hooks, 3 MCP servers.

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 plan

README.md
[![agentmods](https://agentmods.dev/badge/skills/sylorei/claude-godmode/plan.svg)](https://agentmods.dev/skills/sylorei/claude-godmode/plan)
Your own site
<a href="https://agentmods.dev/skills/sylorei/claude-godmode/plan"><img src="https://agentmods.dev/badge/skills/sylorei/claude-godmode/plan.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,381 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00048 $0.03381
Opus 5 $0.00024 $0.01690
Sonnet 5 $0.00010 $0.00676
Haiku 4.5 $0.00005 $0.00338

Measured 7d ago against content hash 2aa3bc3b26d3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

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 7d 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/plan/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Plan

Break the brief for roadmap unit $N into a tactical plan that makes building mechanical: ordered steps, an explicit dependency relationship per step (so /build can group steps into parallel waves), and a verification plan that covers every acceptance criterion from the brief.

Run after /brief N has captured the why + what + spec. The plan is the contract /build N executes against and /verify N checks. This is the third step of the spine: /mission/brief N/plan N/build N/verify N/ship.

The artifact lives in the consumer's repo, alongside the brief it reads:

  • Reads .planning/missions/<mission_id>/briefs/NN-name/BRIEF.md — the brief for roadmap unit $N (mission_id=$("$gm/godmode-state" get mission_id); see the helper-resolution note in Process).
  • Writes .planning/missions/<mission_id>/briefs/NN-name/PLAN.md — the single tactical plan for that unit.

Exactly two artifact files per work unit: BRIEF.md + PLAN.md. Do NOT introduce a third file — no EXECUTE.md, no separate execution-log file. The git log is the execution log. Write PLAN.md and nothing else.


Auto Mode

Auto Mode suppresses confirmation prompts, not the clarifying questions that decide the shape of the plan. In either mode:

  • Ask the consequential questions — a genuinely ambiguous step ordering, an unstated constraint, a design fork where the options diverge materially — when the brief, .planning/PROJECT.md, and the repo can't settle it. Guessing here produces a plan that builds the wrong thing efficiently.
  • Assume the trivial — for low-stakes judgment calls, pick a sensible default and record it under an Assumptions heading rather than asking.
  • Don't re-ask what the brief already decided. Treat user course-corrections as normal input. A plan is a breakdown, not an interview — but the few questions that change the breakdown are worth asking in either mode.

Recommendation convention (godmode:recommend-convention). When you do ask, follow the shared convention in rules/godmode-recommend.md: lead with a Recommended option carrying a visible one-line rationale, then let the user override — never a flat menu of equal choices:

Read the full file on GitHub · 221 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 221 lines · 48 tokens per session scan A 2aa3bc3b26d3

Subscribe to this mod's changes

plan is a skill published in the GitHub repository SyloRei/claude-godmode (3 stars, last pushed 3mo ago), licensed MIT. It adds 48 tokens to every session and 3,381 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.

Related

Other skills, from other repositories