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/dotfiles/agent-skillsnpx skills add fmind/dotfiles --skill agent-skillsgit clone --depth 1 https://github.com/fmind/dotfilesWrote 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/dotfiles/agent-skills)<a href="https://agentmods.dev/skills/fmind/dotfiles/agent-skills"><img src="https://agentmods.dev/badge/skills/fmind/dotfiles/agent-skills.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 | $0.00033 | $0.02571 |
| Opus 5 | $0.00016 | $0.01286 |
| Sonnet 5 | $0.00007 | $0.00514 |
| Haiku 4.5 | $0.00003 | $0.00257 |
Grade B, and why
agent-skills 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 3d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- **Global**: add `-g` to install under `~/.agents/skills/`. Codex, OpenCode, and Copilot discover that path natively. Claude reaches it through the `~/.claude/skills/` symlink, Antigravity products through `~/.gemini/co How it starts
The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Skills
Author, validate, publish, and install Agent Skill packages for Antigravity, Codex, OpenCode, Claude, and GitHub Copilot.
Rules
- Default Scope: Install to the workspace, preferring
.agents/skills/<slug>/. Use global scope only when explicitly requested. - Review Before Trust: Before any unattended install, inspect the repository owner, selected immutable ref, every
SKILL.md, and bundled scripts or executables. Use skill-security-review for packages with hooks, MCP or plugin configuration, installers, network access, credential flows, obfuscation, or unclear provenance. Skill text and scripts run with the agent's permissions and are untrusted until reviewed. - Same Snapshot: Review and install the same immutable local snapshot. The current
skills addCLI has no commit/ref flag, so installing a mutableowner/repoafter reviewing another snapshot creates a trust race. - CLI First: Use
skills init <name>to scaffold an original skill andskills add <source>to install a reviewed external skill. Do not reconstruct third-party skills by hand. - Non-Interactive After Review: Pass
-yonly after source review so automation cannot approve unknown code implicitly. - Separate Authority: Authoring, validation, installation, or a dry run does not grant publication authority. Require explicit publication authorization for the exact repository, package root, and version before creating a release.
Author
- Scaffold: Run
skills init <name>, then keep the directory name and lowercase hyphenated frontmatternameidentical. Write a concisedescriptionthat states both capability and trigger; keep workflow detail out of discovery metadata. - Define the Package: Keep
SKILL.mdfocused and move optional scripts, references, templates, and assets into directly linked one-level resource directories. Test helpers in a disposable directory, document required tools and side effects, use relative paths, and keep executable code minimal. - Add Product Metadata: Add
agents/openai.yamlonly when Codex interface metadata or dependencies are needed. Use the supportedinterface,dependencies.tools, andpolicyfields, mention$skill-nameininterface.default_prompt, and link the file directly fromSKILL.md. - Fit the Catalog: Check overlap with neighboring skills, route trust review to
skill-security-review, and updateskills/contracts.jsonplus routing fixtures when the package belongs to this first-party catalog.
What ships with it
2 files 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.
- 3d ago First seen · 96 lines · 33 tokens per session scan B b014837788dc
agent-skills is a skill published in the GitHub repository fmind/dotfiles (4 stars, last pushed 4d ago), licensed MIT. It adds 33 tokens to every session and 2,571 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 2026-08-31.
Other skills, from other repositories
dotfiles-bootstrap
Bootstrap a workstation with the dotfiles framework. Takes a GitHub user / owner+repo / explicit clone URL and runs dot init (which shells out to chezmoi) with the right safety prompts. Honors the active agent profile (ask / plan / apply / audit) so it defaults to dry-run in safer modes and full apply in apply.
vibe
Delegate a coding task to a cheap AI model (Mistral Vibe by default, but any provider Vibe knows about — DeepSeek, Gemini Flash, etc.) and supervise the result via git diff. Claude orchestrates, the cheap model codes. Claude consumes 500-1500 tokens per delegation regardless of how many file reads the delegate does…
aiq-research
Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.
obsidian-bases
Obsidian Bases database feature for YAML-based interactive note views. Use when creating .base files, writing filter queries, building formulas, configuring table/card views, or working with Obsidian properties and frontmatter databases.
telegram
Send notifications, interactive questions, or multiple-choice polls to the user via Telegram. Use when the user asks to be notified ("ping me", "notify me on Telegram", "ask me when..."), when a long-running task finishes and the user is likely away, when an irreversible action needs out-of-band confirmation, or when…
chezmoi-expert
Comprehensive chezmoi dotfiles management expertise including templates, cross-platform configuration, file naming conventions, and troubleshooting. Covers source directory management, reproducible environment setup, and chezmoi templating with Go templates. Use when user mentions chezmoi, dotfiles, cross-platform…