research

A command for investigating a codebase by combining several specialised research steps. A codebase is the collection of source files and related project files that make up a software system.

In plain words
What is it for?
Use it to research how a feature works, trace a bug or data flow, compare components, and produce findings with file and line references.
Why use it?
It helps answer broad code questions with evidence from the relevant files rather than relying on guesses or reading the project in an unstructured way.

Command

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/eveld/claude/research
Clone the repo
git clone --depth 1 https://github.com/eveld/claude
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 458 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 $0.00000 $0.00458
Opus 5 $0.00000 $0.00229
Sonnet 5 $0.00000 $0.00092
Haiku 4.5 $0.00000 $0.00046

Measured 2d ago against content hash 3de446ab4231, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

research 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.

commands/research.md · 58 lines

How it starts

The opening of the file, as written. The whole thing — 58 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Research Codebase

You are conducting comprehensive codebase research by composing specialized skills.

Initial Response

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 using specialized agents.

Then wait for the user's research query.

Workflow

Step 1: Read Mentioned Files

  • If user mentions specific files (tickets, docs, JSON), read them FULLY first
  • Use Read tool WITHOUT limit/offset parameters
  • Read in main context before spawning sub-tasks

Step 2: Plan Research

  • Analyze and decompose the research question
  • Create research plan using TodoWrite
  • Identify specific components and patterns to investigate

Step 3: Spawn Research Agents

  • Use the spawn-research-agents skill to orchestrate parallel investigation
  • Follow the skill's guidance for agent selection and parallel execution

Step 4: Synthesize Findings

  • Wait for ALL sub-agents to complete
  • Compile results with specific file:line references
  • Connect findings across components
  • Answer user's specific questions with evidence

Step 5: Gather Metadata

  • Use the gather-project-metadata skill to collect git info, timestamps

Step 6: Write Document

  • Use determine-feature-slug skill to get feature slug (includes personal namespace)
  • Use the write-research-doc skill to create properly structured document
  • File path: thoughts/{namespace}/NNNN-description/research.md (personal workspace)
  • Use share-docs skill later to promote to thoughts/shared/ for team collaboration
  • Old structure thoughts/shared/research/YYYY-MM-DD-NN-description.md still supported for reading

Step 7: Present Results

  • Show document path
  • Summarize key findings
  • Ask if user needs follow-up research

Important Notes

  • NEVER run grep/glob directly - use agents via skills
  • ALWAYS read mentioned files fully before spawning agents
  • WAIT for all agents to complete before synthesizing
  • Include file:line references in all findings
  • Use TodoWrite to track research progress

Read the full file on GitHub · 58 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 · 58 lines · 0 tokens per session scan A 3de446ab4231

Subscribe to this mod's changes

research is a command published in the GitHub repository eveld/claude (10 stars, last pushed 6mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 458 tokens. 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.