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 skills add MausRundung/mcp-explorer --skill project-explorergit 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/skills/mausrundung/mcp-explorer/project-explorer)<a href="https://agentmods.dev/skills/mausrundung/mcp-explorer/project-explorer"><img src="https://agentmods.dev/badge/skills/mausrundung/mcp-explorer/project-explorer/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mausrundung/mcp-explorer/project-explorer"><img src="https://agentmods.dev/badge/skills/mausrundung/mcp-explorer/project-explorer.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00039 | $0.01521 |
| Opus 5.5 | $0.00016 | $0.00608 |
| Sonnet 5.5 | $0.00008 | $0.00304 |
| Haiku 4.5 | $0.00004 | $0.00152 |
Grade A, and why
project-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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Project Explorer
Use the project-explorer MCP server to answer structural questions about a
codebase without reading files one by one: what is in the project, what imports
what, where a symbol or pattern occurs, and which npm packages are stale.
The server exposes five usable tools through one STDIO process:
list_allowed_directories, explore_project, search_files, check_outdated,
rename_file. delete_file exists but ships disabled in this plugin's
mcp.json.
Full argument tables: references/tool-reference.md.
When to use
- "What is the structure of this project?", "which files import X?", "how entangled is this module?"
- Broad code search across many files: TODO/FIXME inventories, API usage sites, config keys, dead exports, large recently-changed files.
- Dependency hygiene before a release or upgrade.
- Any task where reading files individually would cost many round trips.
Do not use it as a substitute for opening one known file, and never use it as a mass-edit tool - it only reads, reports, and renames.
Workflow
1. Confirm scope first
Call list_allowed_directories once at the start. Every other tool is
path-restricted to those directories.
- A non-empty list means paths outside it fail with
Access denied. - An empty list means the server has no allow-list and can read anywhere.
Treat that as a signal to pass explicit project-root paths in
mcp.jsonrather than as license to scan the whole disk.
Relative directory / searchPath values resolve against the first allowed
directory, not the editor's cwd - so an unrooted "src" can silently point at
the wrong project. Prefer absolute paths, or verify the first allowed directory
before using a relative one.
2. Map the project
explore_project({ "directory": "/absolute/path/to/project" })
Returns per-file sizes, detected config files, parsed imports/exports/functions,
and a local dependency graph (edge list, most-imported and most-importing
files). JS/TS import edges are resolved through tsconfig baseUrl/paths;
Python, Java, Kotlin, Go, Rust, and C# produce import/export-like declarations
without resolved edges.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 1mo ago Changed 4dee46e6d589
- 1mo ago First seen · 143 lines · 39 tokens per session scan A dd2bbb080c31
project-explorer is a skill published in the GitHub repository MausRundung/mcp-explorer (2 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 1,521 once invoked, about $0.0002 per session on Opus 5.5. 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 skills, from other repositories
feedback-nudge
Use when the user wants to report a bug, request a feature, or send feedback to the Zooza engineering team. Also offer proactively after a successful commit operation (max once per week).
coolify-incident
Triage and respond to Coolify incidents with diagnose, logs, restart, and emergency actions. Use when production is down or degraded.
coolify-diagnose
Investigate Coolify application, server, or fleet-wide issues. Use when triaging errors, health checks, or scan results.
resilireplay
Capture a supported coding-agent tool failure as bounded, sanitized evidence and generate an executable deterministic regression. Use when a user asks to capture, explain, reproduce, or prevent recurrence of a Claude Code, Codex, Hermes, or MCP tool failure, or to validate a ResiliReplay adapter or campaign.
api-errors
McpError constructor, JsonRpcErrorCode reference, and error handling patterns for @cyanheads/mcp-ts-core. Use when looking up error codes, understanding where errors should be thrown vs. caught, or using ErrorHandler.tryCatch in services.
api-linter
MCP definition linter rules reference. Use when bun run lint:mcp or bun run devcheck reports a lint error or warning (format-parity, schema-is-object, name-format, server-json-, etc.) and you need to understand the rule, its severity, and how to fix it. Every rule ID the linter emits has an entry in this doc.