layout

layout is a command for coding agents from AleksandarBisevac/claude-plugins. It costs 93 tokens per session (2,168 once invoked), scanned A, original, MIT.

A command for choosing between two current ways to store an audit manifest: one file, or an index plus separate files for each phase. A phase is a distinct part of a larger plan.

In plain words
What is it for?
Use it to switch between a single-file manifest and a sharded manifest, where phase data is stored separately.
Why use it?
It lets a project match its storage layout to its workflow, such as parallel work in separate worktrees or a plan that has become large. Both layouts remain supported and represent the same schema.

Command

Installs and runs on its own, but its text points at files inside its plugin — anything it tells you to read at a ${CLAUDE_PLUGIN_ROOT} path is only there once the plugin is installed. Installing the plugin gets both.

Part of the audit plugin — 2 skills, 20 commands, 4 agents, 4 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/aleksandarbisevac/claude-plugins/layout
Clone the repo
git clone --depth 1 https://github.com/AleksandarBisevac/claude-plugins

Or install audit, the plugin that ships this one along with the rest of its 2 skills, 20 commands, 4 agents, 4 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 layout

README.md
[![agentmods](https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/layout.svg)](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/layout)
Your own site
<a href="https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/layout"><img src="https://agentmods.dev/badge/commands/aleksandarbisevac/claude-plugins/layout.svg" alt="Measured on agentmods" height="20"></a>
Per session 93 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,168 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 $0.00093 $0.02168
Opus 5 $0.00046 $0.01084
Sonnet 5 $0.00019 $0.00434
Haiku 4.5 $0.00009 $0.00217

Measured 5d ago against content hash 0795f80d63f0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

layout 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.

plugins/audit/commands/layout.md · 142 lines

How it starts

The opening of the file, as written. The whole thing — 142 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/audit:layout — pick the manifest layout, in either direction

Read ${CLAUDE_PLUGIN_ROOT}/reference/orchestrator.md and ${CLAUDE_PLUGIN_ROOT}/reference/manifest-conventions.md first.

Two shapes of the same schema, and every script and hook in this plugin reads both transparently:

  • sharded<manifestPath> is an index (meta · bugs · fileIndex · phase stubs) and each phase's body lives in phases/<phaseId>.json.
  • single-file — the whole manifest is that one file.

Neither is legacy and neither is a stage. Installing a newer plugin never makes a layout change due, staying on single-file never makes a manifest out of date, and /audit:doctor's layout line reports which shape is in use rather than nominating one to fix. If the user asks why the old name for this command was migrate, that is the answer: the name described a direction and read as an age.

What actually decides it — ask about this, never about version numbers:

  • sharded when phases run in parallel from separate worktrees, or when the plan has grown big enough that loading every phase in order to run one costs real context;
  • single-file when it is one session at a time and a handful of phases. One file, one diff, no index to keep in step.

0. Which direction

$ARGUMENTS begins with sharded or single-file. Read the manifest first (conventions → Locating the manifest) and say which layout is in use before anything else, because that is what makes the request meaningful:

  • Already in the requested layout → say so and stop. Nothing to do is a result, not a no-op.
  • No direction in $ARGUMENTS → ask (AskUserQuestion), naming the current layout in the question and phrasing the options by the criterion above — parallel phases across worktrees, or a manifest big enough that per-phase context hurts vs solo work, few phases. Never guess a direction from the current layout: "the other one" is not a decision the user made.

Read the full file on GitHub · 142 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. 5d ago First seen · 142 lines · 93 tokens per session scan A 0795f80d63f0

Subscribe to this mod's changes

layout is a command published in the GitHub repository AleksandarBisevac/claude-plugins (4 stars, last pushed 3d ago), licensed MIT. It adds 93 tokens to every session and 2,168 once invoked, about $0.0005 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.