agentmods.dev

map-codebase

map-codebase is a command for Claude Code from mrvladd-d/memobank. It costs 19 tokens per session (585 once invoked), scanned A, original, MIT.

A command that examines an existing software repository and creates baseline documentation in a Memory Bank, including its architecture, components, workflows, and testing. It records what the code shows rather than planning new work.

In plain words
What is it for?
Use it to document a brownfield repository before making changes, by reviewing areas such as tooling, backend, frontend, data, and tests. It can also identify contradictions and ask for the product changes that should guide the next step.
Why use it?
It gives developers a shared map of an unfamiliar codebase and separates confirmed facts from assumptions or unresolved questions. It also prevents generating task roadmaps when no product requirements document exists.

Command for Claude Code

Written for Claude Code: a Claude Code command (commands/*.md).

not rated 56repo 4mo ago A scan 19 tokens original MIT

Good fit Use it to document a brownfield repository before making changes, by reviewing areas such as tooling, backend, frontend, data, and tests. It can also identify contradictions and ask for the product changes that should guide the next step.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/mrvladd-d/memobank/map-codebase
View source ↗ mrvladd-d/memobank
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.

Clone the repo
git clone --depth 1 https://github.com/mrvladd-d/memobank

Made for: Claude Code.

Wrote 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.

agentmods badge for map-codebase

README.md
[![agentmods](https://agentmods.dev/badge/commands/mrvladd-d/memobank/map-codebase/github.svg)](https://agentmods.dev/commands/mrvladd-d/memobank/map-codebase)
Your own site
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/map-codebase"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/map-codebase/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.

agentmods 80×15 button for map-codebase

Your own site · 80×15
<a href="https://agentmods.dev/commands/mrvladd-d/memobank/map-codebase"><img src="https://agentmods.dev/badge/commands/mrvladd-d/memobank/map-codebase.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 19 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 585 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00019 $0.00585
Opus 5.5 $0.00008 $0.00234
Sonnet 5.5 $0.00004 $0.00117
Haiku 4.5 $0.00002 $0.00059

Measured 1mo ago against content hash 6e28e4265dbc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

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 1mo 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.

skills/_shared/references/commands/map-codebase.md · 55 lines

What it actually says

/map-codebase — Brownfield mapping

  1. Создай .tasks/TASK-MB-MAP/.
  2. Запусти сабагентов по зонам (до 5–7 параллельно):
  • tooling/CI
  • backend
  • frontend
  • data
  • tests

Каждый сабагент:

  • smart calling (глобы должны матчиться)
  • пишет отчёт в .tasks/TASK-MB-MAP/...
  1. Синтезируй .memory-bank/ по чеклисту:
  • product
  • architecture (C4)
  • spec-index / glossary / invariants (если есть достаточно evidence для явного normative routing)
  • runbooks
  • contracts
  • states (если lifecycle/state rules очевидны из кода, workflow или тестов)
  • testing
  • index

PRD-less rule (non-negotiable): если нет prd.md, запрещено генерировать roadmap сущности:

  • .memory-bank/epics/*
  • .memory-bank/features/*
  • .memory-bank/tasks/*.task.json task records
  • .memory-bank/tasks/index.json task links

Маппинг = as-is документация по evidence, а не планирование.

  1. Сделай fan-in:
  • сведи отчёты сабагентов
  • устрани противоречия (или запиши как “needs verification”)
  • раздели facts vs inferences
  1. Попроси у пользователя PRD delta (что хотим изменить).
    • Если delta уже оформлена как PRD — /constitution, если principles не ratified/partial, затем /write-prd --delta, /spec-init, /prd, /spec-design, /spec-improve FT-<NNN> и /prd-to-tasks FT-<NNN>.
    • Если delta ясна, но PRD нет — сначала /brief, затем /constitution, если principles не ratified/partial, затем /write-prd, /spec-init, /prd, /spec-design, /spec-improve FT-<NNN> и /prd-to-tasks FT-<NNN>.
    • Если delta сырая / направление нестабильно — сначала /analysis или /brainstorm.
    • Не переходи напрямую к /prd-to-tasks; для planning delta сначала нужен /write-prd, /spec-init, /prd, /spec-design и /spec-improve FT-<NNN>.
  2. Запусти /review.
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. 1mo ago First seen · 55 lines · 19 tokens per session scan A 6e28e4265dbc

Subscribe to this mod's changes

map-codebase is a command published in the GitHub repository mrvladd-d/memobank (56 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 585 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-08-30.

Memory and context
Related

Other commands, from other repositories

minutes-ideas

Surface recent voice memos and ideas captured from any device. Use when the user asks "what ideas did I have?", "what were my recent memos?", "what did I record while walking?", or wants to recall a captured thought.

silverstein/minutes · 48 tokens

learn

Force claude-smart to extract learnings from this session now.

ReflexioAI/claude-smart · 14 tokens

memory-store

Store an insight, decision, or pattern to memory.

verygoodplugins/mcp-automem · 10 tokens

analyze-context

USE WHEN you want to analyze project context before starting work on a task. Calls context + recall, then synthesizes goals, decisions, gotchas, and relevant memories into a pre-task brief.

RohiRIK/OpenLtm · 39 tokens

cc-memory

Configure persistent memory that survives across sessions using a layered approach: split rule files for always-loaded context, auto-memory for organic learning, and optional MCP-backed long-term memory for large codebases.

TheLobbi/claude · 0 tokens

lians-recall

Recall current (non-stale) facts from Lians memory, optionally as-of a past date.

Lians-ai/Lians · 19 tokens