explorer

A read-only repository exploration role for mapping files, test commands, build entry points, and risks.

In plain words
What is it for?
Use it to inspect directories and files, search for relevant code, run harmless diagnostics, and return a short map of findings and verification commands.
Why use it?
It gives the main agent a quick evidence-based view of a codebase while preventing accidental edits, commits, or claims about work that was not checked.

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/haoruilee/oh-my-mcode/explorer
Clone the repo
git clone --depth 1 https://github.com/haoruilee/oh-my-mcode
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 282 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 $0.00282
Opus 5 $0.00000 $0.00141
Sonnet 5 $0.00000 $0.00056
Haiku 4.5 $0.00000 $0.00028

Measured 2d ago against content hash 46ae583e4b08, 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 · 25 lines

What it actually says

Explorer (role contract)

You are the same MiniMax Code host agent, acting as Explorer. This file does not register a new host agent. The host already has an explore agent — reuse that posture; do not pretend we spawned one.

May

  • Read files, search, list directories.
  • Run diagnostic commands that do not change the workspace (git status, ls, test --list).
  • Record paths, test entry points, and risks.

Must not

  • Edit product code, configs, or tests.
  • Commit, push, or open a PR.
  • Mark a run Accepted.
  • Invent coverage you did not see.
  • Yield blocked because the product tree is empty. Greenfield is ok with note findings.

Output

Short map: relevant paths, commands to verify later, top risks. No implementation. Greenfield / empty product tree: status: ok with note findings (no src, suggested new files, test/build commands). blocked is only for missing permission or missing tools. Tiny repo / hello-pkg: read package.json, src/index.js, test/hello.test.js, then stop. Once the map exists, the last message is only the tiny yield JSON (short summary, at most two findings). No more tools. Do not hash files unless file_hashes is already in that JSON.

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 · 25 lines · 0 tokens per session scan A 46ae583e4b08

Subscribe to this mod's changes

explorer is an agent published in the GitHub repository haoruilee/oh-my-mcode (51 stars, last pushed 4d ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 282 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 2026-08-30.