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.
/plugin marketplace add MadAppGang/magus/plugin install devWrote 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/skills/madappgang/magus/code-roast)<a href="https://agentmods.dev/skills/madappgang/magus/code-roast"><img src="https://agentmods.dev/badge/skills/madappgang/magus/code-roast/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.
<a href="https://agentmods.dev/skills/madappgang/magus/code-roast"><img src="https://agentmods.dev/badge/skills/madappgang/magus/code-roast.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00038 | $0.03008 |
| Opus 5.5 | $0.00015 | $0.01203 |
| Sonnet 5.5 | $0.00008 | $0.00602 |
| Haiku 4.5 | $0.00004 | $0.00301 |
Grade C, and why
code-roast scanned grade C 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 22d 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.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
| **NUCLEAR** | User explicitly says "nuclear" | Scorched earth | Full creative mode, absurdist escalation | "The only fix is `git rm -rf` and starting over. I'm kidding. Mostly." | How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Code Roast Skill
Overview
The Code Roast skill performs a humorous but technically rigorous code quality analysis using a registry of 192 anti-patterns across 8 languages plus universal categories.
Core Rules:
- Cite
file:line— every sin gets a precise location - Punch the code, not the coder — humor targets the artifact, never the author
- Every roast has a fix — no ridicule without redemption
- Severity-sorted — CAPITAL offenses first, parking tickets last
- Three-tier detection — built-in grep always works; CLI tools and cloud APIs are optional bonuses
What it covers: Go, Java, C#, TypeScript/JavaScript, Python, React, HTML/CSS, SQL, universal patterns (SOLID, microservices, testing, CI/CD, dependencies, concurrency), and AI-generated code ("slop") detection.
Phase 0: Load References
Before starting, read the companion files for this skill:
- Read
sin-registry.md— but ONLY the sections relevant to the detected languages in the target code. Do NOT read all 192 patterns if the project is Go-only. - Read
detection-patterns.md— focus on Tier 1 patterns for detected languages, then check Tier 2 tool availability.
Language detection: Look at file extensions in the target scope to determine which language sections to load.
Phase 1: Acquire Target
Determine what code to roast. In priority order:
- User specified files/dirs — if the user said "roast src/auth/", use that
- Changes — if the user said "roast my changes", "roast this PR" or "roast my recent
work", capture the review surfaces with the plugin's script. Never hand-roll a
git diffrange here — three sites once did, and all three were wrong in different ways:
It prints onebun "${CLAUDE_PLUGIN_ROOT}/scripts/capture-review-surfaces.ts" \ --repo "$(git rev-parse --show-toplevel)"##### SURFACE: <label> #####block per surface — branch commits vs base, staged, unstaged, untracked. The target is the set of files those patches touch (--statgives the list without the bodies). If it warns that no base branch resolved, say the roast does not cover committed branch work. If it prints nothing, there is nothing to roast — say so; do not widen to a range of your own. - Full project scan — if the user said "roast everything" or "roast the codebase"
What ships with it
2 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.
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.
- 22d ago Changed b9716854c914
- 1mo ago First seen · 374 lines · 38 tokens per session scan C d0266d29f4a5
code-roast is a skill published in the GitHub repository MadAppGang/magus (13 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 3,008 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…