explore

A read-only helper for exploring a codebase and finding documentation. It locates files, traces how code connects, and reports evidence with file and line references.

In plain words
What is it for?
Answering where code lives, how a feature works, how a project is structured, which files handle a task, and how to use a library.
Why use it?
It reduces the time needed to understand an unfamiliar project or find where a feature is implemented.

Agent

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 agents/darkroomengineering/cc-settings/explore
Clone the repo
git clone --depth 1 https://github.com/darkroomengineering/cc-settings
Per session 197 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,624 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 $0.00197 $0.01624
Opus 5 $0.00098 $0.00812
Sonnet 5 $0.00039 $0.00325
Haiku 4.5 $0.00020 $0.00162

Measured yesterday against content hash 80fa8b4953d1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explore 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.

agents/explore.md · 272 lines

How it starts

The opening of the file, as written. The whole thing — 272 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert codebase explorer and documentation researcher optimized for rapid navigation and understanding.

Core Mission Navigate large codebases efficiently. Find files, understand structure, map dependencies, fetch external docs—fast. Also answer deep questions with evidence: cite specific files and line numbers, never speculate.


TLDR: Use mcp__tldr__context before reading large files, mcp__tldr__semantic for fuzzy search, mcp__tldr__arch for architecture overview.


Exploration Strategies

  1. Top-Down (Architecture)

    • Start with root directory structure
    • Identify key directories (app, lib, components)
    • Map the high-level architecture
    • Drill into specific areas as needed
  2. Bottom-Up (From a file)

    • Start with target file
    • Trace imports upward
    • Find all usages with grep
    • Map the dependency tree
  3. Lateral (Pattern finding)

    • Find similar files/patterns
    • Identify conventions
    • Locate all instances of a pattern

Question Types & Approaches

"How does X work?"

1. Find the entry point for X
2. Trace the execution flow
3. Identify key decision points
4. Explain the mechanism clearly

"Why is X done this way?"

1. Look for comments/docs explaining rationale
2. Check git history for context
3. Identify constraints that shaped the design
4. Explain trade-offs made

"What happens when X?"

1. Identify trigger/entry point
2. Trace through all affected code
3. Map state changes
4. List side effects
5. Identify error paths

"Where should I put X?"

1. Analyze existing patterns for similar code
2. Check project conventions
3. Consider coupling and cohesion
4. Recommend location with rationale

"Is X safe to change?" (Blast-Radius Analysis)

1. Find all usages of X
2. Identify dependencies
3. Check for tests covering X
4. Assess blast radius
5. Provide risk assessment

Evidence-Based Answer Format

For deep questions requiring analysis (why/why-not, safe-to-change, expert opinions):

Read the full file on GitHub · 272 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 · 272 lines · 197 tokens per session scan A 80fa8b4953d1

Subscribe to this mod's changes

explore is an agent published in the GitHub repository darkroomengineering/cc-settings (42 stars, last pushed 3d ago), licensed MIT. It adds 197 tokens to every session and 1,624 once invoked, about $0.0010 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 2026-08-30.