What is repo-analyze?

A repository mapping skill that reports a compact file tree, languages, frameworks, dependencies, entry points, and README highlights. A repository is the folder containing a project’s code and related files.

Use it when you need a project overview, want to know where to start, or need to check whether a repository uses a particular framework such as Next.js, FastAPI, or Rust.

It replaces much of the manual listing and searching needed to understand an unfamiliar project at the start of a session.

repo-analyze — Skill for Claude Code by osouthgate

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.

Any agent

npx skills add osouthgate/agent-plus --skill repo-analyze

Clone the repo

git clone --depth 1 https://github.com/osouthgate/agent-plus

Made for: Claude Code.

Or install repo-analyze, the plugin that ships this one along with the rest of its 1 skill.

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/osouthgate/agent-plus/repo-analyze/github.svg)](https://agentmods.dev/skills/osouthgate/agent-plus/repo-analyze)

Your own site

<a href="https://agentmods.dev/skills/osouthgate/agent-plus/repo-analyze"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/repo-analyze/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/osouthgate/agent-plus/repo-analyze"><img src="https://agentmods.dev/badge/skills/osouthgate/agent-plus/repo-analyze.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 94 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,681 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	$0.00094	$0.01681
Opus 5	$0.00047	$0.00840
Sonnet 5	$0.00019	$0.00336
Haiku 4.5	$0.00009	$0.00168

Measured 9d ago against content hash 6daf72fa5439, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

repo-analyze 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 9d 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.

repo-analyze/skills/repo-analyze/SKILL.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

repo-analyze

The map, not the contents. One call replaces the cold-start dance — file-tree exploration, finding entrypoints, reading every manifest, scanning README. Session mining showed ~67 grep + ~60 ls ops on a typical fresh-repo session, almost all of it answerable from one structured payload.

Tree output is compact by default: one row per directory, showing file counts and per-extension LOC. This stays small even in large repos. Use --tree-mode full when you need the individual file list (e.g. to scan for a specific file that isn't an entrypoint).

Lives at ${CLAUDE_SKILL_DIR}/../../bin/repo-analyze; the plugin auto-adds bin/ to PATH, so just run repo-analyze ....

When to reach for this

User asks "what is this project / what's the tech stack / give me an overview" → run repo-analyze --pretty --tree-mode compact. One call → languages, frameworks, deps, entrypoints, README highlights.
User asks "where do I start" → run repo-analyze --pretty --tree-mode compact and read the entrypoints + readme sections.
User asks "is this a Next.js / FastAPI / Rust project" → run repo-analyze --tree-mode compact and inspect frameworks[]. Each entry has a confidence field (high = manifest-confirmed, medium = config file present but not in manifest).
Cold-starting in any unfamiliar checkout → run this BEFORE the first Read/Glob/Grep.

After running

Read nextSteps[] from the envelope and offer them to the user. Each entry is a short string naming the next recommended action (e.g. "Read src/index.ts — top entrypoint", "skill-plus scan — mine session history for skill candidates", "diff-summary -- summarize staged/unstaged changes or a branch diff"). Surface these as suggested actions at the end of your summary.

Headline command

repo-analyze --tree-mode compact  # always pass explicitly; compact = one row/folder (default, but be explicit)
             [--path PATH]
             [--tree-mode full]   # override: every file listed individually
             [--max-tree-files INT]  # default 200 (full mode only)
             [--max-tree-depth INT]  # default 4
             [--no-readme]           # skip README highlights
             [--output PATH]         # offload to disk
             [--shape-depth 1|2|3]   # envelope detail (default 3)
             [--pretty | --json]
             [--version]

Read the full file on GitHub · 101 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.

9d ago First seen · 101 lines · 94 tokens per session scan A 6daf72fa5439

Subscribe to this mod's changes

repo-analyze is a skill published in the GitHub repository osouthgate/agent-plus (4 stars, last pushed 2mo ago), licensed MIT. It adds 94 tokens to every session and 1,681 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.

Claude Code Debugging agent-tools claude-code-plugin cli

vs-search-tuning-partial-case

Use when the user provides 1-50 concrete bad-case search queries for one Viking Search app and wants local deterministic fixes. This skill only verifies request-level fine-operation interventions against a read-only baseline scene and delivers a console-ready configuration sheet, validated payloads, and a replay…

volcengine/SearchCLI · 85 tokens

vs-search

Search runtime and scene management: verify queries, inspect scenes, debug app readiness, and diagnose recall or scene-config issues.

volcengine/SearchCLI · 27 tokens

debugging-workflows

Systematic troubleshooting for Falcon Foundry CLI errors, manifest validation failures, deploy failures, artifact runtime errors, and development server issues. TRIGGER when user encounters CLI errors, foundry ui run not working, deploy failures, authentication issues, function execution failures, "debug my function"…

CrowdStrike/foundry-skills · 90 tokens

repo-analyze

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

repo-analyze

When to reach for this

After running

Headline command

What this file has done since we first saw it

Other skills, from other repositories

vs-search-tuning-partial-case

vs-search

debugging-workflows

sentry

systematic-debugging

debugging