roast-repo

roast-repo is a command for Claude Code from kid-sid/claude-spellbook. It costs 0 tokens per session (1,058 once invoked), scanned A, original, MIT.

A command that examines a code repository and gives a pointed review of bugs, code smells, security weaknesses, and untidy engineering practices. Each finding must include a suggested fix.

In plain words
What is it for?
Run it to review source code, tests, configuration, dependencies, recent commits, and common maintainability or security issues.
Why use it?
It provides a focused review of technical problems that may be missed during routine development. The repository is inspected before findings are reported.

Command for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Run it to review source code, tests, configuration, dependencies, recent commits, and common maintainability or security issues.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/kid-sid/claude-spellbook/roast-repo
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.

Clone the repo
git clone --depth 1 https://github.com/kid-sid/claude-spellbook

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 roast-repo

README.md
[![agentmods](https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/roast-repo/github.svg)](https://agentmods.dev/commands/kid-sid/claude-spellbook/roast-repo)
Your own site
<a href="https://agentmods.dev/commands/kid-sid/claude-spellbook/roast-repo"><img src="https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/roast-repo/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.

agentmods 80×15 button for roast-repo

Your own site · 80×15
<a href="https://agentmods.dev/commands/kid-sid/claude-spellbook/roast-repo"><img src="https://agentmods.dev/badge/commands/kid-sid/claude-spellbook/roast-repo.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,058 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00000 $0.01058
Opus 5 $0.00000 $0.00529
Sonnet 5 $0.00000 $0.00212
Haiku 4.5 $0.00000 $0.00106

Measured 11d ago against content hash de5b8b8e4647, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

roast-repo scanned grade A with 1 finding 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 11d 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- `eval()`, `exec()`, `shell=True` / `child_process.exec` with non-literal input
.claude/commands/roast-repo.md · 92 lines

How it starts

The opening of the file, as written. The whole thing — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Deliver a brutally honest, technically sharp roast of the current repository. Spot real bugs, code smells, security holes, and engineering sloppiness. Be pointed and witty, but every finding must be accurate and include a fix.

Instructions

Phase 1: Reconnaissance

  1. Run git ls-files to enumerate all tracked files.
  2. Detect the primary language(s) from file extensions.
  3. Read README.md (if present), CI config (.github/workflows/, Makefile, etc.), and package manifests (package.json, requirements.txt, go.mod, Cargo.toml, etc.).
  4. Collect repo stats: total files, source files, test files, lines of code (git ls-files | xargs wc -l 2>/dev/null | tail -1).
  5. Check last 20 commit messages: git log --oneline -20.

Phase 2: Code Quality (refactor skill patterns)

Scan source files for:

  • Functions / methods longer than 30 lines
  • Nesting deeper than 3 levels
  • Magic numbers (bare literals that aren't 0, 1, or -1)
  • Commented-out code blocks
  • TODO / FIXME without a linked issue number
  • Duplicate or near-duplicate logic blocks
  • Boolean parameters (use named options/enums)
  • God classes (> 10 methods or > 200 lines)
  • Long parameter lists (> 4 params)

Phase 3: Security (security-scan skill patterns)

Scan all files for:

  • Hardcoded secrets: patterns like AKIA, sk-, ghp_, Bearer, password =, secret =, token = with string values
  • Private keys: -----BEGIN (RSA|EC|OPENSSH) PRIVATE KEY-----
  • Connection strings with embedded credentials
  • eval(), exec(), shell=True / child_process.exec with non-literal input
  • SQL string concatenation
  • debug=True or DEBUG=True in non-dev config files

Phase 4: Test Coverage

  • Count test files vs source files. Ratio below 0.5 is suspicious.
  • Flag source directories with zero corresponding test files.
  • Look for test files that only test the happy path (single assert or no edge-case names).
  • Flag any critical-sounding module (auth, payment, crypto) with no test file.

Phase 5: Engineering Hygiene

  • Check .gitignore for common missing entries: .env, node_modules/, __pycache__/, *.pyc, dist/, build/, .DS_Store
  • Check for committed secrets or build artifacts that should be gitignored
  • Check dependency versions: floating (^, ~, *, >=) vs pinned — flag if more than half are unpinned
  • Check commit messages for quality: one-word commits (fix, wip, asdf, update), no conventional-commit style
  • Flag any file > 500 lines that isn't a lock file or generated file

Read the full file on GitHub · 92 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. 11d ago First seen · 92 lines · 0 tokens per session scan A de5b8b8e4647

Subscribe to this mod's changes

roast-repo is a command published in the GitHub repository kid-sid/claude-spellbook (188 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,058 tokens. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.