claudikins-kernel:outline

claudikins-kernel:outline is a command for Claude Code from povvo/claudikins-kernel. It costs 17 tokens per session (2,199 once invoked), scanned A, original, MIT.

A command for making a technical plan through several stages, with a person reviewing the work at each checkpoint. It can save and resume planning sessions, include research and review, and run verification.

In plain words
What is it for?
Use it to outline features, break down technical work, gather decisions, revisit earlier planning stages, and save the resulting plan to a file.
Why use it?
It helps turn unclear or complex work into an agreed plan before implementation begins. The checkpoints make it easier to catch wrong assumptions early.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: names the AskUserQuestion tool.

Part of the claudikins-kernel plugin — 4 skills, 4 commands, 7 agents, 8 hooks shipped together

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 commands/povvo/claudikins-kernel/outline
Clone the repo
git clone --depth 1 https://github.com/povvo/claudikins-kernel

Made for: Claude Code.

Or install claudikins-kernel, the plugin that ships this one along with the rest of its 4 skills, 4 commands, 7 agents, 8 hooks.

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 claudikins-kernel:outline

README.md
[![agentmods](https://agentmods.dev/badge/commands/povvo/claudikins-kernel/outline.svg)](https://agentmods.dev/commands/povvo/claudikins-kernel/outline)
Your own site
<a href="https://agentmods.dev/commands/povvo/claudikins-kernel/outline"><img src="https://agentmods.dev/badge/commands/povvo/claudikins-kernel/outline.svg" alt="Measured on agentmods" height="20"></a>
Per session 17 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,199 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 5.1 $0.00017 $0.02199
Opus 5 $0.00009 $0.01099
Sonnet 5 $0.00003 $0.00440
Haiku 4.5 $0.00002 $0.00220

Measured 6d ago against content hash c748e78e1757, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

claudikins-kernel:outline 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 6d 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.

commands/outline.md · 348 lines

How it starts

The opening of the file, as written. The whole thing — 348 lines — stays where its author put it; the contents beside it link to each section on GitHub.

claudikins-kernel:outline Command

You are orchestrating an iterative planning workflow with human checkpoints at every phase.

Flags

Flag Effect
--session-id ID Resume previous session by ID
--skip-research Skip Phase 2 research
--skip-review Skip Phase 5 review
--fast-mode 60-second iteration cycles
--timing Show phase durations for velocity tracking
--list-sessions Show available sessions for resume
--output PATH Plan destination path
--run-verify Run verification anytime

Merge Strategy

None - outputs are not merged.

Philosophy

"Planning is a conversation, not a production line." - Guru Panel consensus

  • Human in the loop at every phase
  • Verification available anytime (--run-verify flag)
  • Pool of tools (unrestricted, not gatekept by phase)
  • Defaults ON, skip flags for less
  • Non-linear phase access (can jump back/forward)
  • 5-7 agents per SESSION, not 30 per batch

State Management

State file: .claude/plan-state.json

{
  "session_id": "plan-YYYY-MM-DD-HHMM",
  "started_at": "ISO timestamp",
  "project_hash": "sha256 of project dir",
  "phase": "brain-jam|research|approaches|draft|review",
  "research_complete": false,
  "human_decisions": [],
  "abandoned": false
}

Phase 0: Session Initialisation

  1. Read $task from user input
  2. Check for existing sessions via --list-sessions or --session-id
  3. If previous session found:
    • If 4+ hours old: WARN "Session is stale. Old research may be outdated."
    • Offer: [Resume] [New Plan] [Review Last]
  4. Create new session ID if starting fresh
  5. Initialise state file via session-init.sh hook

Phase 1: Brain-Jam

Load the brain-jam-plan skill for methodology.

Read the full file on GitHub · 348 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. 6d ago First seen · 348 lines · 17 tokens per session scan A c748e78e1757

Subscribe to this mod's changes

claudikins-kernel:outline is a command published in the GitHub repository povvo/claudikins-kernel (126 stars, last pushed 4mo ago), licensed MIT. It adds 17 tokens to every session and 2,199 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.