A repository layout audit and guided cleanup for making an AI coding agent find, read, and verify project files with less searching. It checks structure, names, generated files, and runtime-created names before proposing small approved changes.

Use it to review a repository's file map, naming, build-output placement, toolchain information, and verification commands, then apply the agreed improvements.

Poor layout makes an agent spend time guessing where files are and reading irrelevant or oversized files. This identifies those obstacles without changing anything until the owner approves each step.

repo-layout — Skill for Claude Code and Codex by V-Songbird/slag

Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code

/plugin marketplace add V-Songbird/slag

Claude Code

/plugin install anneal

Made for: Claude Code, Codex.

Or install anneal, the plugin that ships this one along with the rest of its 4 skills, 1 agent, 2 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/v-songbird/slag/repo-layout/github.svg)](https://agentmods.dev/skills/v-songbird/slag/repo-layout)

Your own site

<a href="https://agentmods.dev/skills/v-songbird/slag/repo-layout"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/repo-layout/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/v-songbird/slag/repo-layout"><img src="https://agentmods.dev/badge/skills/v-songbird/slag/repo-layout.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 167 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 4,023 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00167	$0.04023
Opus 5.5	$0.00067	$0.01609
Sonnet 5.5	$0.00033	$0.00805
Haiku 4.5	$0.00017	$0.00402

Measured today against content hash 42e3c8a22cb6, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

repo-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 today.

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.

anneal/skills/repo-layout/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repo layout

Make an existing repository cheaper for an agent to work in: fewer searches to find a file, fewer reads to understand it, one command to check a change. The target conventions and the reason for each are in references/conventions.md. Read that file before building a plan. No change is a valid result.

Argument: $ARGUMENTS. A host that does not fill that in leaves it as written; read the argument from the request instead. When it is audit, run steps 1 and 2 only, then stop without changing any file. Write no file outside the project either: read the audit's --json report from the command itself or through a pipe, never from a saved copy. A findings, report or notes file in the project is a change too, even when standing instructions ask to save findings: show the findings in the reply, offer to save them, and write that file only after an explicit yes. When nobody can answer, as in a headless or automated run, write nothing.

What differs by host

Three things in this procedure have a different name on each host. The notes after the table cover the other host differences.

	Claude Code	Codex	Antigravity
The plugin's own files	`${CLAUDE_PLUGIN_ROOT}/`	resolve `../../` from this `SKILL.md`	resolve `../../` from this `SKILL.md`
Asking the owner to choose	`AskUserQuestion`, `multiSelect`	ask in the reply and wait	`ask_question`, `is_multi_select`
The layout survey (step 5)	the `anneal:mapper` subagent	a read-only subagent, or inline	`invoke_subagent`, `TypeName: "research"`

Where a host has no subagent to delegate to, do the survey inline and keep it short: read the audit's JSON and the files it names, not the tree.

On Antigravity, give every command the project root the person named as its working directory, the Cwd of run_command. Without it, commands can run in Antigravity's own scratch directory instead of the project. When the person named no project root, ask for it before running anything.

Read the full file on GitHub · 167 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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.

today Changed 42e3c8a22cb6
4d ago Changed a8aecbc57453
9d ago Changed · +10 lines b5d4d31e9eb5
10d ago Changed · +3 lines 99a7087609ad
1mo ago Changed b718b7bf06b6
1mo ago Changed · +29 lines 00ef32b0297a
1mo ago First seen · 125 lines · 167 tokens per session scan A 9d7d95d67db7

Subscribe to this mod's changes

repo-layout is a skill published in the GitHub repository V-Songbird/slag (1 stars, last pushed today), licensed MIT. It adds 167 tokens to every session and 4,023 once invoked, about $0.0007 per session on Opus 5.5. 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 2026-09-23.

Building agents Productivity

repo-layout next to 6 skills from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
repo-layoutV-Songbird/slag	Skill	1	today	MIT	A	167	Claude Code, Codex
orbit-notionnexu-io/open-design	Skill	108k	today	Apache-2.0	A	117	Claude Code, Codex
agentmailpaperclipai/paperclip	Skill	114k	today	MIT	A	30	Claude Code, Codex
rowboat-spacesrowboatlabs/rowboat	Skill	18k	yesterday	Apache-2.0	A	60	Claude Code, Codex
Cortexdanielmiessler/LifeOS	Skill	20k	9d ago	MIT	A	184	Claude Code
pinchtab-mcppinchtab/pinchtab	Skill	11k	4d ago	MIT	A	52	Claude Code, Codex
feishuHmbown/CodeWhale	Skill	41k	7d ago	MIT	A	33	Claude Code, Codex