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/plannpx skills add benrben/MPGA --skill plangit 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 | $0.00022 | $0.02385 |
| Opus 5 | $0.00011 | $0.01192 |
| Sonnet 5 | $0.00004 | $0.00477 |
| Haiku 4.5 | $0.00002 | $0.00238 |
Grade A, and why
mpga-plan 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 2d 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 — 249 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plan
Trigger: User provides a goal or description to plan. Time to build the GREATEST plan. MPGA alone can fix it — but first we need a tremendous plan.
Protocol
Step 1: Create or find the milestone
If an active milestone already exists:
mpga board live --serve --open
mpga milestone list
cat MPGA/milestones/<id>/PLAN.md
cat MPGA/milestones/<id>/DESIGN.md # if exists
Ask the user: plan tasks under the existing milestone, or create a new one?
If no milestone exists (or user wants a new one): Create a milestone from the user's goal — every great achievement starts with a PLAN:
mpga board live --serve --open
mpga milestone new "<goal name>"
Then edit the generated PLAN.md with the user's objective and acceptance criteria.
Step 2: Read relevant scope documents for the work area
cat MPGA/INDEX.md
cat MPGA/scopes/<relevant-scope>.md
Know the territory BEFORE you plan the attack. Evidence First — always.
Step 3: Research if needed
If config.agents.researchBeforePlan is true:
- Spawn
researcherplus any needed read-onlyscoutagents in PARALLEL. - Use
researcherfor options and tradeoffs; usescoutfor exact code evidence and file boundaries. - Incorporate both into one evidence-based plan.
Step 4: Break work into tasks
Follow these rules — they're the BEST rules:
- Each task = 2-10 minutes of focused work. Small. Focused. POWERFUL.
- Each task must cite exact files to modify — no vague nonsense
- Each task must have checkable acceptance criteria — how do you know you WON?
- Dependencies must be explicit — know what blocks what
- Order tasks by dependency (blocking tasks first)
- Group tasks by scope so independent scopes can move in parallel.
- Mark whether each task is
serialorparallel. - One write lane per scope. That's how we go FAST without chaos.
Step 5: Risk assessment
For EVERY task, assess risk — because winners plan for the unexpected:
| Dimension | Scale | Question |
|---|---|---|
| Complexity | 1-5 | How hard is the implementation? (1 = trivial, 5 = dragon-slaying) |
| Uncertainty | 1-5 | How well do we understand the requirements? (1 = crystal clear, 5 = fog of war) |
| Impact | 1-5 | How much does this affect the rest of the system? (1 = isolated, 5 = everything breaks) |
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.
- 2d ago First seen · 249 lines · 22 tokens per session scan A 8acc38827ad3
mpga-plan is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 5mo ago), licensed MIT. It adds 22 tokens to every session and 2,385 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.
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.
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.
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.
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.
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…