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/gus2708/sftp-manager/agents-mdgit clone --depth 1 https://github.com/Gus2708/sftp-managerWrote 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/gus2708/sftp-manager/agents-md)<a href="https://agentmods.dev/instructions/gus2708/sftp-manager/agents-md"><img src="https://agentmods.dev/badge/instructions/gus2708/sftp-manager/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 | $0.02568 | $0.02568 |
| Opus 5 | $0.01284 | $0.01284 |
| Sonnet 5 | $0.00514 | $0.00514 |
| Haiku 4.5 | $0.00257 | $0.00257 |
Grade A, and why
sftp-manager 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 4d 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 — 236 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for an AI agent that has been handed this repository.
This file follows the AGENTS.md convention and is read automatically by Codex, Cursor, Jules, Copilot, Zed and others. Claude Code reads CLAUDE.md, which points here.
What this repo is
sftp-manager is a stdio MCP server. It gives an AI agent sandboxed SFTP access to game
servers (Pterodactyl / TaroHosting panels and any plain SFTP host) so configs can be read and
edited, addons installed, backups restored and the server restarted — without a shell.
It is not a library to import and not a service to deploy. The deliverable is a process launched over stdio by an MCP client:
<python> <repo>/mcp_server.py
Everything else in this file exists to get that command running correctly.
Installing it (do this in order)
install_mcp.py is the install and diagnosis surface. It uses only the standard library, so
it runs before any dependency is installed, and every subcommand prints JSON so you can
branch on the result instead of parsing prose.
Step 1 — Diagnose
python install_mcp.py check
Returns Python version, missing dependencies, whether config exists, the exact command/args
to register, and a siguiente_paso field telling you what to do next. Read siguiente_paso
and follow it. If listo is true, skip to step 4.
Step 2 — Dependencies
python install_mcp.py deps
Requires Python 3.10+. If the environment is externally managed (PEP 668) this fails; create a virtualenv and use its interpreter for every later step:
python -m venv .venv
.venv/bin/python install_mcp.py deps # Windows: .venv\Scripts\python.exe
Only paramiko, python-dotenv and mcp are needed to run the server. nbtlib unlocks the two
level.dat tools; anthropic is only for the optional standalone CLI.
Step 3 — Credentials
python install_mcp.py init
This copies servers.example.json → servers.json and .env.example → .env. Both are
git-ignored. It never overwrites an existing file.
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.
- 4d ago First seen · 236 lines · 2,568 tokens per session scan A 61b25492c160
sftp-manager AGENTS.md is an instructions file published in the GitHub repository Gus2708/sftp-manager (0 stars, last pushed 17d ago), licensed MIT. It adds 2,568 tokens to every session, about $0.0128 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.
Other instructions, from other repositories
llm-council CLAUDE.md
Claude Code instructions for amiable-dev/llm-council, covering claude.md — technical notes for llm council, project overview, running & developing, architecture: the l1→l4 layer model (adr-024) and module map (src/llmcouncil/).
openings-mcp AGENTS.md
Instructions for amikai/openings-mcp, a project described as: 💼 One MCP server to search job boards and company career sites.
mimirs CLAUDE.md
Claude Code instructions for TheWinci/mimirs, a project described as: Local MCP server that gives AI coding agents persistent, searchable memory of your codebase.
pubcrawl CLAUDE.md
Claude Code instructions for nickjlamb/pubcrawl, covering claude.md, project overview, commands, testing and architecture.
steam-games-mcp AGENTS.md
Instructions for Grinv/steam-games-mcp, covering agents.md, project shape, commands, conventions and testing the live/published server.
brapi-mcp-server AGENTS.md
Instructions for cyanheads/brapi-mcp-server, covering agent protocol, what's next?, core rules, patterns and tool — connection bootstrap.