What is mpga-map-codebase?

A tool for building and refreshing a map of a software project’s files, structure, and supporting evidence. It offers a quick update and a deeper scan for major changes.

Use it to initialise a project map, refresh documentation about the codebase, check whether evidence links are still valid, find drift, and view a project health report.

It reduces the time spent figuring out how an unfamiliar or recently changed codebase is organised. It also helps identify outdated project information and possible inconsistencies.

mpga-map-codebase — Skill by benrben

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/map-codebase

Any agent

npx skills add benrben/MPGA --skill map-codebase

Clone the repo

git clone --depth 1 https://github.com/benrben/MPGA

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,107 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.

Model	Per session	Once invoked
Fable 5	$0.00032	$0.01107
Opus 5	$0.00016	$0.00553
Sonnet 5	$0.00006	$0.00221
Haiku 4.5	$0.00003	$0.00111

Measured yesterday against content hash 2f79de3f5296, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

mpga-map-codebase 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.

mpga-plugin/skills/map-codebase/SKILL.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

map-codebase

Trigger: User runs /mpga:map, asks to map or sync the codebase, or MPGA/ is stale. Time to MAP this thing.

Modes

Mode	Flag	When to use	Speed
Quick (default)	(none)	Everyday refresh — rebuild INDEX.md, scope files, evidence links	~30 seconds
Deep	`--deep`	First init, major refactors, or user wants full parallel scout mapping	Minutes

Default is quick — fast and sufficient for everyday use. Use --deep when you need the FULL treatment.

Quick Mode Protocol (default)

Fast rebuild of the MPGA knowledge layer from current codebase state — a FRESH start, TREMENDOUS results. Make Project Great Again, one scope at a time.

Check if MPGA is initialized:
```
mpga status 2>/dev/null || echo "NOT_INITIALIZED"
```
If not initialized: run mpga init --from-existing first — gotta lay the FOUNDATION
Run full sync — regenerate EVERYTHING:
```
mpga sync --full
```
Verify evidence health — check the INTEGRITY:
```
mpga evidence verify
```
Run drift check — find the PROBLEMS:
```
mpga drift --report
```
Show health report — the SCOREBOARD:
```
mpga health
```

Quick mode output

Summary of files scanned and scopes generated — the NUMBERS
Evidence health percentage — our SCORE
Any drift detected — what needs FIXING
Recommended next steps — the PATH FORWARD

Quick mode rules

Always run full sync, not incremental, when user explicitly requests sync — go BIG
Report the number of scopes generated and evidence links found — TRANSPARENCY
If evidence coverage is below threshold, note it prominently — Fake docs detected! We don't hide BAD numbers, we FIX them

Deep Mode Protocol (`--deep`)

Full parallel codebase mapping using multiple scout agents — the FASTEST way to document a codebase.

If this is the first map, run a full sync to generate scope scaffolds with static analysis — the FOUNDATION:
```
mpga sync --full
```
If MPGA already exists and only part of the repo changed, prefer:
```
mpga sync --incremental
```

Read the full file on GitHub · 128 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.

yesterday First seen · 128 lines · 32 tokens per session scan A 2f79de3f5296

Subscribe to this mod's changes

mpga-map-codebase is a skill published in the GitHub repository benrben/MPGA (5 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 1,107 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.

Writing and docs

systematic-debugging

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

obra/superpowers · 21 tokens

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…

vercel/next.js · 95 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

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

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…

vercel/next.js · 170 tokens