Instructions for using the dora command-line tool to explore a codebase through its indexed code structure. It helps locate definitions and uses of symbols, dependencies, and architectural relationships.

Use it to find where code is defined or used, inspect dependencies, map packages, and assess the likely impact of a change.

It reduces the time spent searching through files when you need to understand how a codebase is organized or what a change might affect. The guidance separates structural exploration from reading and editing source files.

dora — Skill for Claude Code and Codex by butttons

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.

Any agent

npx skills add butttons/dora --skill docs

Clone the repo

git clone --depth 1 https://github.com/butttons/dora

Made for: Claude Code, Codex.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/butttons/dora/docs/github.svg)](https://agentmods.dev/skills/butttons/dora/docs)

Your own site

<a href="https://agentmods.dev/skills/butttons/dora/docs"><img src="https://agentmods.dev/badge/skills/butttons/dora/docs/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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/butttons/dora/docs"><img src="https://agentmods.dev/badge/skills/butttons/dora/docs.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 24 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,866 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.

Model	Per session	Once invoked
Fable 5.1	$0.00024	$0.02866
Opus 5.5	$0.00010	$0.01146
Sonnet 5.5	$0.00005	$0.00573
Haiku 4.5	$0.00002	$0.00287

Measured 1mo ago against content hash 554091d7432f, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

dora 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.

src/templates/docs/SKILL.md · 345 lines

How it starts

The opening of the file, as written. The whole thing — 345 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Philosophy

IMPORTANT: Use dora FIRST for ALL code exploration tasks.

dora understands code structure, dependencies, symbols, and architectural relationships through its indexed database. It provides instant answers about:

Where symbols are defined and used
What depends on what (and why)
Architectural patterns and code health
Impact analysis for changes

When to use dora vs other tools:

dora: Code exploration, symbol search, dependency analysis, architecture understanding
Read: Reading actual source code after finding it with dora
Grep: Only for non-code files, comments, or when dora doesn't have what you need
Edit/Write: Making changes after understanding with dora
Bash: Running tests, builds, git commands

Workflow pattern:

Use dora to understand structure and find relevant code
Use Read to examine the actual source
Use Edit/Write to make changes
Use Bash to test/verify

Commands

Overview

dora status - Check index health, file/symbol counts, last indexed time
dora map - Show packages, file count, symbol count

Files & Symbols

dora ls [directory] [--limit N] [--sort field] - List files in directory with metadata (symbols, deps, rdeps). Default limit: 100
dora file <path> - Show file's symbols, dependencies, and dependents. Note: includes local symbols (parameters).
dora symbol <query> [--kind type] [--limit N] - Find symbols by name across codebase
dora refs <symbol> [--kind type] [--limit N] - Find all references to a symbol
dora exports <path> - List exported symbols from a file. Note: includes function parameters.
dora imports <path> - Show what a file imports

Dependencies

dora deps <path> [--depth N] - Show file dependencies (what this imports). Default depth: 1
dora rdeps <path> [--depth N] - Show reverse dependencies (what imports this). Default depth: 1
dora adventure <from> <to> - Find shortest dependency path between two files

Read the full file on GitHub · 345 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

SNIPPET.md 3.5 KB

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.

1mo ago First seen · 345 lines · 24 tokens per session scan A 554091d7432f

Subscribe to this mod's changes

dora is a skill published in the GitHub repository butttons/dora (109 stars, last pushed 7mo ago), licensed MIT. It adds 24 tokens to every session and 2,866 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.

Claude Code Debugging ai-agent bun cli code-analysis code-intelligence

roam

Codebase comprehension via roam-code CLI. Use when exploring codebases, planning modifications, debugging failures, assessing PR risk, or checking architecture health. Triggers on: understanding project structure, pre-change safety checks, finding symbols/files, blast radius analysis, affected tests, health scoring…

Cranot/roam-code · 86 tokens

smiles-validation

Strict SMILES validation, structural comparison, and modification verification. Catches invalid LLM-generated molecules.

synthetic-sciences/openscience · 24 tokens

ix

Answer structural questions about a codebase — what a symbol is, what calls it, what a change breaks, where the hotspots are — from a persistent code graph via the ix CLI, instead of grepping.

ix-infrastructure/Ix · 44 tokens

confirm-failures-are-causally-linked-to-the-task-before-reportin

When delegating a task affected by this skill, include.

ZaxbyHub/opencode-swarm · 29 tokens

isolate-the-specific-failure-mode-before-proposing-a-fix