sessions

sessions is a command for Claude Code from 0xUXDesign/ai-codebase-boilerplate. It costs 11 tokens per session (1,703 once invoked), scanned A, original, MIT.

A command that turns a product requirements document (PRD) or research document into ready-to-copy prompts for separate Claude Code work sessions. It divides the work into related units and considers their dependencies and complexity.

In plain words
What is it for?
Use it to organize parallel development from a written plan, especially when changes span several files, modules, or features.
Why use it?
It removes the manual work of deciding how to split a large implementation into manageable pieces. Each unit is planned as one session, worktree, and pull request.

Command 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 commands/0xuxdesign/ai-codebase-boilerplate/sessions
Clone the repo
git clone --depth 1 https://github.com/0xUXDesign/ai-codebase-boilerplate

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 sessions

README.md
[![agentmods](https://agentmods.dev/badge/commands/0xuxdesign/ai-codebase-boilerplate/sessions.svg)](https://agentmods.dev/commands/0xuxdesign/ai-codebase-boilerplate/sessions)
Your own site
<a href="https://agentmods.dev/commands/0xuxdesign/ai-codebase-boilerplate/sessions"><img src="https://agentmods.dev/badge/commands/0xuxdesign/ai-codebase-boilerplate/sessions.svg" alt="Measured on agentmods" height="20"></a>
Per session 11 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,703 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 $0.00011 $0.01703
Opus 5 $0.00005 $0.00851
Sonnet 5 $0.00002 $0.00341
Haiku 4.5 $0.00001 $0.00170

Measured 3d ago against content hash 22000799fe61, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sessions 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 3d 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.

template/.claude/commands/sessions.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Generate self-contained, copy-paste-ready prompts for parallel Claude Code sessions that implement a PRD or research document.

Input Resolution

  1. If $ARGUMENTS is provided and non-empty, use it as the doc path
  2. If no argument: run ls -t docs/plans/*.md docs/sessions/*.md 2>/dev/null | head -1 to find the most recently modified doc
  3. If nothing found, ask the user which file to use
  4. Print the resolved doc path prominently so the user can confirm before proceeding:
    Document: docs/plans/dashboard-fixes-prd.md
    
  5. Read the full document content

Analysis

Analyze the document and determine:

Work Units

  • Identify logical work units — groups of related changes that should ship as one PR
  • A work unit has cohesive scope: same module area, same feature, or tightly coupled changes
  • Each work unit = one session = one worktree = one PR

Complexity Assessment

  • Simple (1 session): single file or 2-3 files, straightforward changes, no schema changes
  • Medium (1 session, but more steps): 3-5 files, may include schema changes or new functions
  • Complex (consider splitting): 6+ files, multiple modules, schema + logic + UI changes

Dependency Graph

  • Which units depend on others? (e.g., schema changes must land before code that uses them)
  • Which units are fully independent and can run in parallel?
  • Draw the dependency graph explicitly

Output Format

Summary

Start with a brief breakdown:

## Session Breakdown

**Document:** <path>
**Sessions:** <N> implementation + <0 or 1> review = <total> total
**Parallelization:** Sessions <X> and <Y> can run in parallel. Session <Z> depends on <X>.

| Session | Scope | Files | Depends On |
|---------|-------|-------|------------|
| 1       | ...   | ~N    | —          |
| 2       | ...   | ~N    | —          |
| 3       | ...   | ~N    | 1          |
| R       | Review all sessions against plan | —  | All above |

Session Prompts

For each session, generate a fenced code block containing a complete, self-contained prompt. The prompt must work when pasted into a fresh Claude Code window with zero prior context.

Read the full file on GitHub · 195 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. 3d ago First seen · 195 lines · 11 tokens per session scan A 22000799fe61

Subscribe to this mod's changes

sessions is a command published in the GitHub repository 0xUXDesign/ai-codebase-boilerplate (11 stars, last pushed 5mo ago), licensed MIT. It adds 11 tokens to every session and 1,703 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.