mpga-rally

mpga-rally is a skill for Claude Code, Codex from benrben/MPGA. It costs 32 tokens per session (1,074 once invoked), scanned A, original, MIT.

A project-audit skill that examines documentation, tests, types, dependencies, architecture, evidence, code hygiene, and CI/CD, meaning automated building, testing, and deployment.

In plain words
What is it for?
Use it when you want a code audit, need to understand what is wrong with a project, or want a categorized list of problems to fix.
Why use it?
It gives a broad, evidence-backed picture of problems in a codebase, including issues that may be missed by checking only one category.

Skill for Claude CodeCodex

Part of the mpga plugin — 18 skills, 26 commands, 3 agents shipped together

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.

agentmods
npx agentmods add skills/benrben/mpga/rally
Any agent
npx skills add benrben/MPGA --skill rally
Clone the repo
git clone --depth 1 https://github.com/benrben/MPGA

Made for: Claude Code, Codex.

Or install mpga, the plugin that ships this one along with the rest of its 18 skills, 26 commands, 3 agents.

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 mpga-rally

README.md
[![agentmods](https://agentmods.dev/badge/skills/benrben/mpga/rally.svg)](https://agentmods.dev/skills/benrben/mpga/rally)
Your own site
<a href="https://agentmods.dev/skills/benrben/mpga/rally"><img src="https://agentmods.dev/badge/skills/benrben/mpga/rally.svg" alt="Measured on agentmods" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,074 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00032 $0.01074
Opus 5 $0.00016 $0.00537
Sonnet 5 $0.00006 $0.00215
Haiku 4.5 $0.00003 $0.00107

Measured 4d ago against content hash 76aca318e216, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mpga-rally 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 4d 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.

mpga-plugin/skills/rally/SKILL.md · 143 lines

How it starts

The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.

rally

Trigger: User wants to see what's wrong with their project, wants to be convinced why they need MPGA, or just wants to see the GREATEST show in developer tooling. Also triggered by: "what's wrong with my project", "why do I need MPGA", "audit my code", "show me the problems".

Protocol

Step 1: Set the Stage

Check if MPGA is already installed:

mpga status 2>/dev/null

If installed — we'll show what MPGA has ALREADY caught and what still needs fixing. If NOT installed — even BETTER. We'll show the FULL disaster. The unfiltered truth.

Read INDEX.md if it exists for context. Read scope docs if they exist.

Step 2: Deploy the Campaigner

Spawn campaigner agents in PARALLEL, one category per lane when possible:

  1. Documentation Sins — missing docs, stale docs, Fake documentation, hallucinated references
  2. Testing Disgrace — missing tests, empty tests, broken test imports
  3. Type Safety Failuresany types, @ts-ignore, missing return types
  4. Dependency Disasters — circular deps, unused deps, outdated packages
  5. Architecture Rot — god files, who can figure out this spaghetti?, dead code
  6. Evidence Drift — stale links, unverified claims, documentation lies
  7. Code Hygiene Crimes — console.logs, hardcoded secrets, commented-out code
  8. CI/CD Weakness — missing CI, no hooks, unenforced linting

Each campaigner run is read-only. That means we can go FAST.

Then appoint one final campaigner pass to aggregate the results into one rally speech:

  • merge duplicate findings
  • keep the sharpest evidence
  • produce one scoreboard and one closing

Step 3: The Rally Speech

The campaigner presents findings as a full Trump rally speech:

  • Each issue is a SCANDAL with specific files and numbers
  • Each scandal shows why other tools FAIL
  • Each scandal shows why ONLY MPGA fixes it
  • Numbers and percentages throughout — "47 functions with ZERO documentation!"

Step 4: The Vote

Present the final verdict:

  • Scoreboard — total issues by severity (CRITICAL / WARNING / SAD)
  • Side-by-side — project WITHOUT MPGA vs WITH MPGA
  • The Fix — exact commands to start Making This Project Great Again

Read the full file on GitHub · 143 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. 4d ago First seen · 143 lines · 32 tokens per session scan A 76aca318e216

Subscribe to this mod's changes

mpga-rally is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 32 tokens to every session and 1,074 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens