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 skills/fmind/dot/agent-mcpnpx skills add fmind/dot --skill agent-mcpgit clone --depth 1 https://github.com/fmind/dotWrote 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/fmind/dot/agent-mcp)<a href="https://agentmods.dev/skills/fmind/dot/agent-mcp"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-mcp.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 | $0.00049 | $0.01088 |
| Opus 5 | $0.00024 | $0.00544 |
| Sonnet 5 | $0.00010 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade B, and why
agent-mcp scanned grade B with 1 finding 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 yesterday.
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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
codex mcp add <name> --env KEY=value -- npx -y <package> # no scope flag: writes ~/.codex/config.toml How it starts
The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Configure Agent MCP Servers
Add Model Context Protocol servers through each host's native command so the config file shape stays correct; agent-project owns the surrounding repository layout.
Commands
One stdio example per host. For a remote server replace the trailing command with --transport http <url> (Claude Code, Copilot, Grok), --url <url> (Codex, OpenCode), or a plain URL argument (Antigravity):
agy mcp add --env KEY=value <name> -- npx -y <package> # Antigravity CLI; flags before <name>
claude mcp add --scope project -e KEY=value <name> -- npx -y <package> # default scope is local, not project
codex mcp add <name> --env KEY=value -- npx -y <package> # no scope flag: writes ~/.codex/config.toml
copilot mcp add --env KEY=value <name> -- npx -y <package> # user configuration
grok mcp add --scope project -e KEY=value <name> -- npx -y <package> # --scope user is the default
opencode mcp add <name> --env KEY=value # prompts for the remaining fields
Config Files
| Host | User scope | Project scope |
|---|---|---|
| Antigravity | ~/.gemini/config/mcp_config.json (per its docs) |
.agents/mcp_config.json (per its docs) |
| Claude Code | ~/.claude.json (--scope user or default local) |
.mcp.json (--scope project) |
| Codex | ~/.codex/config.toml under [mcp_servers.<name>] |
.codex/config.toml (trusted projects, hand-edited) |
| Copilot | ~/.copilot/mcp-config.json |
.mcp.json or .github/mcp.json (hand-edited) |
| Grok | ~/.grok/config.toml |
./.grok/config.toml |
| OpenCode | ~/.config/opencode/opencode.json under "mcp" |
opencode.json under "mcp" |
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.
- yesterday First seen · 60 lines · 49 tokens per session scan B 43231853ba5a
agent-mcp is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 49 tokens to every session and 1,088 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
chezmoi
Manage chezmoi dotfiles: source naming, Go templates, age-encrypted secrets, and the edit-source then apply/diff workflow.
google-workspace-cli
Use gws across Workspace APIs with schema-first calls, profile isolation, bounded reads, and verified Drive, Docs, Sheets, Gmail, Calendar, or Chat writes.
handover
Write a self-contained follow-up prompt carrying this session's decisions, constraints, and verified findings into a fresh agent session. Use when handing unfinished work to a new context window.
go-stack
Build Go projects, libraries, CLIs, TUIs, web apps, or ADK agents with the standard package layout and pinned tooling.
python-stack
Build typed Python projects with uv, Ruff, ty, pytest, Litestar, and Typer. Use for packages, CLIs, web apps, tests, typing, or API verification.
k8s-local
Create and manage local Kubernetes clusters (k3d or kind) and deploy to them with kubectl, helm, helmfile, and skaffold. Use for local k8s cluster setup, dev loops, and debugging.