mpga-ask

A way to answer questions about how code works by reading project documentation and linking to evidence in the codebase. It focuses on the smallest relevant parts of the project.

In plain words
What is it for?
Use it for questions such as how a feature works, where something is implemented, or what a part of the code does.
Why use it?
It reduces guesswork when locating code or explaining behavior, and makes the answer easier to verify.

Skill for Claude CodeCodex

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

Made for: Claude Code, Codex.

Per session 28 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,153 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 $0.00028 $0.01153
Opus 5 $0.00014 $0.00576
Sonnet 5 $0.00006 $0.00231
Haiku 4.5 $0.00003 $0.00115

Measured 2d ago against content hash 9ce5f77e689c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mpga-ask 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.

mpga-plugin/skills/ask/SKILL.md · 107 lines

How it starts

The opening of the file, as written. The whole thing — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.

ask

Evidence-backed answers. Evidence First — always.

Trigger: User asks "how does X work?", "where is X?", "what does X do?".

The Winning Protocol

  1. Read MPGA/INDEX.md for scope registry — find the SMALLEST relevant scopes first. Precision, people. We don't do sloppy.
  2. Read relevant scope document(s) — the answers are in there.
  3. Answer the question using evidence links as citations — evidence, not guessing.
  4. If the answer is incomplete — and sometimes, very rarely, it happens:
    • Spawn one read-only scout per missing scope in PARALLEL.
    • Ask each scout for evidence, traces, and unknowns only for its assigned scope.
    • Merge the findings into one answer.
  5. If the answer is already in scope docs, do NOT rescan the whole codebase.
  6. NEVER modify any files — read-only.

Confidence Scoring — We Rate EVERYTHING, Total Transparency

Rate EVERY claim in the answer with a confidence level — because we don't hide, we don't hedge, we SCORE:

  • HIGH — Directly verified in source code or scope docs. You read the file, you saw the line, it's RIGHT THERE.
    • Format: [HIGH] <claim> — [E] path/to/file.ts:42 :: functionName()
  • MEDIUM — Inferred from patterns, naming conventions, or related code. Reasonable but not directly confirmed.
    • Format: [MEDIUM] <claim> — inferred from [E] path/to/file.ts:42 :: similar pattern
  • LOW — Educated guess based on general knowledge or incomplete evidence. Could be WRONG.
    • Format: [LOW] <claim> — no direct evidence found, based on <reasoning>

If the overall answer confidence is LOW, say so upfront: "This answer has LOW confidence — consider verifying with a scout or reading the code directly."

Source Citations — Show Your Receipts, Always

Every claim MUST cite the specific source — no citations, no credibility. It's very simple:

  • For code: [E] src/module/file.ts:42-67 :: functionName() — <what it does>
  • For scope docs: [E] MPGA/scopes/<scope>.md — <what it says>
  • For config files: [E] path/to/config.json:key.path — <what it configures>
  • If no source exists: [Unknown] <claim> — not documented, needs investigation

Read the full file on GitHub · 107 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. 2d ago First seen · 107 lines · 28 tokens per session scan A 9ce5f77e689c

Subscribe to this mod's changes

mpga-ask is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It adds 28 tokens to every session and 1,153 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.

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

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

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…

openai/codex · 114 tokens

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…

openai/codex · 113 tokens