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.
npx agentmods add commands/aleksandarbisevac/claude-plugins/layoutgit clone --depth 1 https://github.com/AleksandarBisevac/claude-pluginsWrote 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.
[](https://agentmods.dev/commands/aleksandarbisevac/claude-plugins/layout)<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>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.
| Model | Per session | Once 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 |
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.
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 inphases/<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.
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.
- 5d ago First seen · 142 lines · 93 tokens per session scan A 0795f80d63f0
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.
Other commands, from other repositories
post
Post the current OCR review to a GitHub PR.
show
Display a past OCR review session.
history
List past OCR review sessions.
overlay-apply
Apply NIST 800-53 overlays (FedRAMP, DoD, Privacy, etc.) to existing baselines.
sdlc
Master orchestrator for the complete 5-phase SDLC pipeline. Runs all phases sequentially with approval gates and handoffs between each phase. Organizes artifacts into handoffs/, docs/, and projects/ directories.
pillar-guidance
Deep dive guidance on DORA's 5 pillars and implementation requirements.