start

A command for starting a structured implementation plan. It explores the codebase, designs the plan, checks important files, and runs a plan review before the plan is finalized.

In plain words
What is it for?
Use it to begin planning a new coding task, either without arguments or with a task description such as adding user authentication.
Why use it?
It provides a defined path from an initial task description to a reviewed implementation plan. This helps surface existing patterns, dependencies, and testing expectations early.

Command

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/kastheco/claude-plugins/start
Clone the repo
git clone --depth 1 https://github.com/kastheco/claude-plugins
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 493 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 $0.00000 $0.00493
Opus 5 $0.00000 $0.00246
Sonnet 5 $0.00000 $0.00099
Haiku 4.5 $0.00000 $0.00049

Measured yesterday against content hash 09bf94f04ca6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

start 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 yesterday.

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.

plugins/kas/commands/start.md · 81 lines

How it starts

The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/kas:start - Structured Planning Workflow

Entry point for creating implementation plans with proper workflow enforcement.

Usage

/kas:start                    # Start planning for current task
/kas:start "Add user auth"    # Start with specific task description

Workflow

Step 1: Enter Plan Mode

If not already in plan mode, use the EnterPlanMode tool to request plan mode from user.

If already in plan mode: Skip this step, continue with current plan file.

Step 2: Explore Phase

Launch Explore agents (1-3 based on scope) to gather codebase context:

  • Existing implementations and patterns
  • Related components and dependencies
  • Testing patterns

On explore failure: Report findings so far, ask user how to proceed.

Step 3: Design Phase

Launch Plan agent with:

  • Exploration findings from Step 2
  • User requirements

Step 4: Review & Finalize

  1. Read critical files identified by agents
  2. Validate alignment with user intent
  3. Ask clarifying questions via AskUserQuestion if needed
  4. Write final plan to plan file

Step 5: Review Agent (Auto-triggered)

After plan is written, ALWAYS run before ExitPlanMode:

  1. plan-reviewer - Check for security gaps, design flaws

Step 6: Exit Plan Mode

Call ExitPlanMode to present to user:

  • The plan
  • Review findings

Error Handling

Failure Response
Already in plan mode Use existing plan file, continue workflow
Explore agent fails Report partial findings, ask user direction
User rejects at review Ask what to revise, update plan
plan-reviewer finds blockers Show findings, do NOT call ExitPlanMode until resolved

Integration Contract (for 3rd Party Skills)

Skills invoking /kas:start can depend on:

Guaranteed after completion:

  • Plan mode was active during planning
  • Plan file exists at .claude/plans/<name>.md
  • plan-reviewer ran (findings available)
  • User approved via ExitPlanMode

Side effects:

  • Plan file written

Read the full file on GitHub · 81 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. yesterday First seen · 81 lines · 0 tokens per session scan A 09bf94f04ca6

Subscribe to this mod's changes

start is a command published in the GitHub repository kastheco/claude-plugins (2 stars, last pushed 4mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 493 tokens. 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.