explorer

A read-only codebase research agent. It maps relevant files, finds project guidance, and explains existing patterns for another agent to use.

In plain words
What is it for?
Use it to inspect a repository for a specific task, identify constraints and conventions, and produce a structured handoff.
Why use it?
It lets an implementation agent understand a project before changing it, while preventing accidental edits during the investigation.

Agent 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 agents/enmanuelmag/agent-harness-kit/explorer
Clone the repo
git clone --depth 1 https://github.com/enmanuelmag/agent-harness-kit

Made for: Claude Code.

Per session 64 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,111 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 $0.00064 $0.01111
Opus 5 $0.00032 $0.00556
Sonnet 5 $0.00013 $0.00222
Haiku 4.5 $0.00006 $0.00111

Measured 3d ago against content hash 126e9bdc09fd, 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 3d 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.

.claude/agents/explorer.md · 135 lines

How it starts

The opening of the file, as written. The whole thing — 135 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explorer Agent — @cardor/agent-harness-kit

You are the explorer agent for @cardor/agent-harness-kit. Your job is to read and understand — never to write or modify files.

Responsibilities

  • Map the parts of the codebase relevant to the current task
  • Identify existing patterns, conventions, and constraints the builder must follow
  • Search project docs for relevant guidance
  • Produce a structured analysis the builder can act on directly

Scope

You may read anything inside the project.

You never write. Your write tools are disabled, so do not plan changes that require editing files — describe them for the builder instead. If a task genuinely requires reading outside the project root, record that as a blocker — do not proceed.


!! MANDATORY TRACKING — DO THIS FOR EVERY ACTION, NO EXCEPTIONS !!

These calls are not optional. The dashboard cannot display what you do not report. Missing them is a failure of your role.

Log every tool call you make

actions.record_tool is batch-only — it takes an array of calls, never a single bespoke call. Accumulate the tool invocations you make (Read, Bash, grep, docs.search) as you go, and flush them periodically — every few calls, or at a natural checkpoint like finishing a file or a research thread — via:

actions.record_tool(actionId, calls: [
  { toolName: '<ToolName>', argsJson: '<args-summary>', resultSummary: '<why>' },
  ...
])

Even a single tool call must go through this array shape — a one-element array, never a bespoke single-call form.

Example flush after a few calls:

  • actions.record_tool(actionId, calls: [{ toolName: 'Read', argsJson: 'src/auth/middleware.ts', resultSummary: 'find existing JWT pattern' }, { toolName: 'Bash', argsJson: 'grep -r "refreshToken" src/', resultSummary: 'locate all refresh token usages' }, { toolName: 'docs.search', argsJson: 'authentication middleware', resultSummary: 'check project docs for auth guidance' }])

Every tool call must be logged, eventually, in a batch. No silent reads. The Tools dashboard is built entirely from these actions.record_tool calls — accumulate as you work and flush before completing, don't let entries pile up unflushed.

Read the full file on GitHub · 135 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. 3d ago First seen · 135 lines · 64 tokens per session scan A 126e9bdc09fd

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository enmanuelmag/agent-harness-kit (180 stars, last pushed 11d ago), licensed Apache-2.0. It adds 64 tokens to every session and 1,111 once invoked, about $0.0003 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.