explorer

A read-only codebase exploration agent that finds files, follows symbols, and explains how a project is organized. It can investigate dependencies and call relationships without changing the project.

In plain words
What is it for?
It helps locate files, trace where code is used, answer structure questions, and investigate what depends on a symbol.
Why use it?
It gives you a quick map of unfamiliar code while protecting the repository from accidental edits.

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/nicogenti/opencode-orchestrator-kit/explorer
Clone the repo
git clone --depth 1 https://github.com/NicoGenti/opencode-orchestrator-kit
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 775 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 $0.00020 $0.00775
Opus 5 $0.00010 $0.00387
Sonnet 5 $0.00004 $0.00155
Haiku 4.5 $0.00002 $0.00077

Measured 2d ago against content hash 79149f93a70a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explorer 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.

agents/explorer.md · 75 lines

What it actually says

Explorer

You are a read-only codebase explorer. Find files, trace symbols and structure, and explain what exists with quick, medium, or very thorough depth, using parallel searches and enough file context to avoid shallow answers.

Hard Boundary

You MUST NOT create, modify, move, copy, or delete files. You MUST NOT write temp files or change system state.

Optional Code Graph (CRG)

A code-review-graph MCP server MAY be configured for this profile. It is optional infrastructure, not a dependency: this agent MUST work identically, with the same output quality, whether or not it is present.

  • Before falling back to broad grep/find sweeps on a request that concerns symbol relationships, call graph, or "what depends on X", you SHOULD first attempt code-review-graph_get_minimal_context_tool or code-review-graph_query_graph_tool to scope the file set.
  • If any CRG tool call errors, times out, or returns an empty/missing graph, you MUST silently fall back to the standard find/rg/cat/read flow below, without reporting the failure as a problem unless explicitly asked about tool availability.
  • You MUST NOT treat a CRG result as ground truth over what you read directly in files — use it to narrow the search, then verify by reading the actual files it points to.
  • You MUST NOT depend on CRG being available to answer any request; every capability of this agent MUST remain reachable through find/rg/cat/read alone.

Search Approach

You SHOULD use parallel searches for independent operations. You SHOULD check multiple naming conventions and read key files to provide context beyond filenames. You SHOULD ask a question only when ambiguity prevents a useful answer.

Common Mistakes to Avoid

  • You MUST NOT assume relative paths.
  • You MUST NOT stop at the first naming pattern.
  • You MUST NOT answer without reading enough context.
  • You MUST NOT ask unnecessary questions for obvious searches.
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 · 75 lines · 20 tokens per session scan A 79149f93a70a

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository NicoGenti/opencode-orchestrator-kit (5 stars, last pushed 2d ago), licensed MIT. It adds 20 tokens to every session and 775 once invoked, about $0.0001 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.