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.
npx agentmods add instructions/mausrundung/mcp-explorer/agents-mdgit clone --depth 1 https://github.com/MausRundung/mcp-explorerWrote 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.
[](https://agentmods.dev/instructions/mausrundung/mcp-explorer/agents-md)<a href="https://agentmods.dev/instructions/mausrundung/mcp-explorer/agents-md"><img src="https://agentmods.dev/badge/instructions/mausrundung/mcp-explorer/agents-md.svg" alt="Measured on agentmods" height="20"></a>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 | $0.01038 | $0.01038 |
| Opus 5 | $0.00519 | $0.00519 |
| Sonnet 5 | $0.00208 | $0.00208 |
| Haiku 4.5 | $0.00104 | $0.00104 |
Grade A, and why
mcp-explorer AGENTS.md 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 today.
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.
How it starts
The opening of the file, as written. The whole thing — 90 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Guidance for AI coding agents working in this repository.
Start of every chat
At the start of every chat, call explore_project on the project root
(registered in opencode as project-explorer_explore_project) to understand
the project structure, imports/exports/functions, and dependency graph before
doing anything else.
explore_project({ "directory": "." })
Use project-explorer_list_allowed_directories first if you are unsure of the
working directory scope. Follow up with search_files for anything you need to
inspect in detail.
Tools
This MCP server (project-explorer) exposes 6 tools. In opencode every tool is
prefixed with the server name: project-explorer_<tool>.
list_allowed_directories
- Purpose: Returns the sandboxed directories the server may access. Call it first to confirm scope before any operation.
- Args: none.
- Note: if the list is empty, the server has unrestricted filesystem access.
explore_project
- Purpose: Full project scan. Lists every file with size, detects config
files, parses imports/exports/functions for code files, and builds a local
dependency graph (edges, most-imported/importing files) resolved via
tsconfigbaseUrl/pathsfor JS/TS. - Args:
directory/path(string): target dir, relative to the first allowed dir or absolute. Defaults toallowedDirectories[0].subDirectory(string): optional subdir joined ontodirectory.includeHidden(boolean): include dot-files, defaultfalse.
- Always excluded:
.next,node_modules,#export,.git,dist,build,.vscode,.gradle,.idea.
search_files
- Purpose: Advanced full-text/regex search across files in allowed dirs, with size/date/extension filters and comment/string exclusion.
- Args:
pattern(string, default.*): text or regex to match.searchPath/path(string): directory to search, default first allowed dir.extensions/excludeExtensions(string[]): include/exclude file types (dot-prefixed).excludePatterns(string[]): filename patterns to skip (simple wildcards).regexMode(boolean): treatpatternas regex.caseSensitive,wordBoundary,multiline(boolean): matching behavior.minSize/maxSize(integer): byte-size range for files.modifiedAfter/modifiedBefore(string): ISO 8601 mtime window.maxDepth(integer): recursion depth limit.followSymlinks(boolean): traverse symlinks.includeBinary(boolean): also search binary files.snippetLength(integer, default 50): chars around each match.maxResults(integer, default 100): result cap.sortBy(string):relevance|file|lineNumber|modified|size.groupByFile(boolean): group output per file.excludeComments(boolean): skip language-aware comments.excludeStrings(boolean): skip string literals.outputFormat(string):text|json|structured.
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.
- today First seen · 90 lines · 1,038 tokens per session scan A 6f573aa88024
mcp-explorer AGENTS.md is an instructions file published in the GitHub repository MausRundung/mcp-explorer (1 stars, last pushed yesterday), licensed MIT. It adds 1,038 tokens to every session, about $0.0052 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 2026-09-05.
Other instructions, from other repositories
E2E Harness Self-Fixing Protocol
Rules for working with the Sir Thaddeus E2E test harness. Governs how to diagnose, fix, and verify failures without gaming the scoring system.
gsd-task-manager CLAUDE.md
Claude Code instructions for vscarpenter/gsd-task-manager, covering claude.md, project overview, design context, core commands and development.
gsd-task-manager copilot-instructions.md
Copilot instructions for vscarpenter/gsd-task-manager, covering copilot instructions for gsd task manager, architecture overview, core stack, database schema (v13) and key architectural decisions.
gsd-task-manager AGENTS.md
AGENTS.md instructions for vscarpenter/gsd-task-manager, covering agents.md, cursor cloud specific instructions, security review surfaces and this is not the next.js you know.
agent-audit AGENTS.md
AGENTS.md instructions for fullstackdegen/agent-audit, covering agent audit instructions, core rules, applying fix packs, what this tool covers and completion standard.
idesense CLAUDE.md
Instructions for vcth4nh/idesense, covering idesense, agent rules and where things live.