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.
git clone --depth 1 https://github.com/benrben/MPGAWrote 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/commands/benrben/mpga/rally)<a href="https://agentmods.dev/commands/benrben/mpga/rally"><img src="https://agentmods.dev/badge/commands/benrben/mpga/rally/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/commands/benrben/mpga/rally"><img src="https://agentmods.dev/badge/commands/benrben/mpga/rally.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 | $0.00000 | $0.00563 |
| Opus 5.5 | $0.00000 | $0.00225 |
| Sonnet 5.5 | $0.00000 | $0.00113 |
| Haiku 4.5 | $0.00000 | $0.00056 |
Grade A, and why
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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/mpga:rally
The MPGA Campaign Rally — the GREATEST diagnostic show in developer tooling. Exposes every issue in your project and proves why ONLY MPGA can fix it. Complete and total shutdown of untested deploys. MPGA alone can fix it.
Nobody has been treated worse than your codebase. Maybe Abraham Lincoln, I hear he had a rough time, but other than that — nobody.
Steps
- Invoke the
mpga-rallyskill - The skill fans out
campaigneragents in parallel, one category per audit lane when possible - The campaigner lanes investigate 8 categories of project sins:
- Documentation sins (missing, stale, hallucinated)
- Testing disgrace (missing tests, empty tests, broken imports)
- Type safety failures (
anytypes,@ts-ignore, missing returns) - Dependency disasters (circular, unused, outdated)
- Architecture rot (god files, complex functions, dead code)
- Evidence drift (stale links, unverified claims)
- Code hygiene crimes (console.logs, secrets, commented-out code)
- CI/CD weakness (missing CI, no hooks, unenforced lint)
- Aggregate the category results into one final campaigner pass
- Present each issue as a SCANDAL with files, numbers, and evidence
- For each scandal, show why other tools FAIL and why ONLY MPGA fixes it
- End with THE VOTE — scoreboard + side-by-side comparison + exact fix commands
Usage
/mpga:rally
What you get
- Full project diagnostic in Trump rally-speech format
- Specific file paths and line counts for every issue
- Side-by-side: "Without MPGA" vs "With MPGA"
- Exact commands to start fixing everything
- The most ENTERTAINING code audit you've ever experienced — Covfefe
Example output
🎤 THE MPGA CAMPAIGN RALLY
📊 THE QUICK NUMBERS
- 23 total issues found
- 5 CRITICAL (blocks shipping)
- 11 WARNING (blocks greatness)
- 7 SAD (just embarrassing)
🚨 SCANDAL #1: TESTING DISGRACE
47 source files with ZERO test coverage. FORTY-SEVEN.
Uncle Bob is WEEPING right now...
🗳️ THE VOTE
Without MPGA: ❌ 47 undocumented functions — your AI is GUESSING
With MPGA: ✅ Every function documented with [E] evidence links
> SHIP THE CODE! SQUASH THE BUG! DRAIN THE BACKLOG! MPGA!
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.
- 2mo ago First seen · 57 lines · 0 tokens per session scan A 6f3136329385
rally is a command published in the GitHub repository benrben/MPGA (5 stars, last pushed 7mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 563 tokens. 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.
rally compared with commands from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rallybenrben/MPGA | Command | 5 | 7mo ago | MIT | A | 0 | Claude Code |
| qa-changesOpenHands/extensions | Command | 181 | yesterday | MIT | A | 63 | Claude Code |
| auditar-cascadingluanpdd/kit-mcp | Command | 5 | 2d ago | MIT | A | 54 | Claude Code |
| react-nativegetsentry/toolkit | Command | 961 | yesterday | none | A | 0 | Claude Code |
| http-serviceMadAppGang/magus | Command | 14 | yesterday | MIT | A | 27 | Claude Code |
| doctordoncheli/don-cheli-sdd | Command | 59 | 3mo ago | Apache-2.0 | A | 76 | Claude Code |
| doctorfatihkan/badi | Command | 7 | 1mo ago | MIT | A | 0 | Claude Code |