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.
npx agentmods add skills/benrben/mpga/developnpx skills add benrben/MPGA --skill developgit clone --depth 1 https://github.com/benrben/MPGAWhat 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 | $0.00029 | $0.01313 |
| Opus 5 | $0.00015 | $0.00656 |
| Sonnet 5 | $0.00006 | $0.00263 |
| Haiku 4.5 | $0.00003 | $0.00131 |
Grade A, and why
mpga-develop 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 yesterday.
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 — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.
develop
Trigger: Plan approved, ready to execute a task. Time to Make Project Great Again.
This is the canonical TDD execution protocol. The
/mpga:executecommand delegates here — use/mpga:developfor all TDD cycle work.
Protocol
For each task in todo column (or a specified task):
-
Claim the task — it's OURS now: Start the live board in the browser through Node first:
mpga board live --serve --openThen claim the task:
mpga board claim <task-id>Claim the scope-local write lane too. One writer per scope. ALWAYS.
-
Load context — know what we're building:
- Read task card:
cat MPGA/board/tasks/<task-file>.md - Read relevant scope docs:
cat MPGA/scopes/<scope>.md - Each TDD task runs in a focused context with only relevant scopes loaded.
- If another task is already writing to that scope, pick a different ready task.
- Read task card:
-
red-green micro-cycle phase — the HEART of TDD:
- Spawn
red-devagent with task + scope context - red-dev writes ONE failing test (starting with degenerate case) — bar turns RED
- Spawn
green-devagent to make that ONE test pass with minimal code — bar turns GREEN - red-dev writes the NEXT test (slightly more complex) — bar turns RED again
- green-dev makes it pass — bar turns GREEN again
- Build complexity progressively: degenerate → simple → complex → edge cases
- Repeat until all acceptance criteria are covered — EVERY SINGLE ONE
- If handoff cost is dominating and the same scope/fixture is still hot, red-dev MAY queue one additional failing test. Never more than two outstanding red tests.
- If green-dev signals "retreat-to-green" (architecture blocks): spawn blue-dev for structural refactoring, then resume micro-cycle
- While red-dev/green-dev own the write lane,
scoutandauditormay run in the background as read-only helpers - Update stage:
mpga board update <id> --tdd-stage redmpga spoke 'RED phase done. Tests written and failing. Green-dev, your move.' - Then:
mpga board update <id> --tdd-stage greenmpga spoke 'GREEN phase done. All tests passing. Minimal code. Blue-dev, clean it up.'
- Spawn
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.
- yesterday First seen · 123 lines · 29 tokens per session scan A 344141f5cde2
mpga-develop is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It adds 29 tokens to every session and 1,313 once invoked, about $0.0001 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.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
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…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…