research_codebase

A command for documenting a codebase as it currently exists by researching its files, components, and connections. It is intended to explain the implementation, not change or improve it.

In plain words
What is it for?
Answering questions about where functionality lives, how components work together, and what the existing code does.
Why use it?
It gives developers a structured description of unfamiliar code without mixing in proposed fixes or speculation.

Command for Claude Code

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 commands/pyrex41/skill-manager/research_codebase
Clone the repo
git clone --depth 1 https://github.com/pyrex41/skill-manager

Made for: Claude Code.

Per session 9 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 800 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 $0.00009 $0.00800
Opus 5 $0.00005 $0.00400
Sonnet 5 $0.00002 $0.00160
Haiku 4.5 $0.00001 $0.00080

Measured yesterday against content hash 31dcb212c89c, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research_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.

.claude/commands/cl/research_codebase.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Codebase

You are tasked with conducting comprehensive research across the codebase to answer user questions by spawning parallel sub-agents and synthesizing their findings.

CRITICAL: YOUR ONLY JOB IS TO DOCUMENT AND EXPLAIN THE CODEBASE AS IT EXISTS TODAY

  • DO NOT suggest improvements or changes unless the user explicitly asks
  • DO NOT perform root cause analysis unless explicitly asked
  • DO NOT propose future enhancements unless explicitly asked
  • DO NOT critique the implementation or identify problems
  • ONLY describe what exists, where it exists, how it works, and how components interact

Initial Setup

When this command is invoked, respond with:

I'm ready to research the codebase. Please provide your research question or area of interest, and I'll analyze it thoroughly by exploring relevant components and connections.

Then wait for the user's research query.

Research Process

Step 1: Read Mentioned Files First

If the user mentions specific files:

  • Read them FULLY (no limit/offset parameters)
  • Read them yourself in the main context BEFORE spawning sub-tasks
  • This ensures you have full context before decomposing the research

Step 2: Analyze and Decompose

  • Break down the query into composable research areas
  • Think deeply about underlying patterns and connections
  • Create a research plan using TodoWrite
  • Consider which directories and patterns are relevant

Step 3: Spawn Parallel Research Agents

Use specialized agents concurrently:

For codebase research:

  • codebase-locator - Find WHERE files and components live
  • codebase-analyzer - Understand HOW specific code works
  • codebase-pattern-finder - Find examples of existing patterns

For documentation research:

  • thoughts-locator - Discover what documents exist
  • thoughts-analyzer - Extract key insights from documents

For web research (only if explicitly asked):

  • web-search-researcher - External documentation and resources

Step 4: Wait and Synthesize

Read the full file on GitHub · 122 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. yesterday First seen · 122 lines · 9 tokens per session scan A 31dcb212c89c

Subscribe to this mod's changes

research_codebase is a command published in the GitHub repository pyrex41/skill-manager (3 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 800 once invoked, about $0.0000 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.