agent-skills

agent-skills is a skill for Claude Code, Codex from fmind/dotfiles. It costs 33 tokens per session (2,571 once invoked), scanned B, original, MIT.

A toolkit for creating, checking, sharing, and installing Agent Skill packages—reusable instructions and resources for coding agents.

In plain words
What is it for?
Use it to create new skills, review external skills before trusting them, validate packages, publish them, or install them for supported coding agents.
Why use it?
It helps maintain the package metadata, safety checks, installation process, and discovery details that skills need.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/fmind/dotfiles/agent-skills
Any agent
npx skills add fmind/dotfiles --skill agent-skills
Clone the repo
git clone --depth 1 https://github.com/fmind/dotfiles

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for agent-skills

README.md
[![agentmods](https://agentmods.dev/badge/skills/fmind/dotfiles/agent-skills.svg)](https://agentmods.dev/skills/fmind/dotfiles/agent-skills)
Your own site
<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>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,571 The whole file, excluding the scripts and references it only reads on demand.
Security scan B 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce 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

Measured 3d ago against content hash b014837788dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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
skills/agent-skills/SKILL.md · 96 lines

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

  1. Default Scope: Install to the workspace, preferring .agents/skills/<slug>/. Use global scope only when explicitly requested.
  2. 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.
  3. Same Snapshot: Review and install the same immutable local snapshot. The current skills add CLI has no commit/ref flag, so installing a mutable owner/repo after reviewing another snapshot creates a trust race.
  4. CLI First: Use skills init <name> to scaffold an original skill and skills add <source> to install a reviewed external skill. Do not reconstruct third-party skills by hand.
  5. Non-Interactive After Review: Pass -y only after source review so automation cannot approve unknown code implicitly.
  6. 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

  1. Scaffold: Run skills init <name>, then keep the directory name and lowercase hyphenated frontmatter name identical. Write a concise description that states both capability and trigger; keep workflow detail out of discovery metadata.
  2. Define the Package: Keep SKILL.md focused 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.
  3. Add Product Metadata: Add agents/openai.yaml only when Codex interface metadata or dependencies are needed. Use the supported interface, dependencies.tools, and policy fields, mention $skill-name in interface.default_prompt, and link the file directly from SKILL.md.
  4. Fit the Catalog: Check overlap with neighboring skills, route trust review to skill-security-review, and update skills/contracts.json plus routing fixtures when the package belongs to this first-party catalog.

Read the full file on GitHub · 96 lines

Files

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.

Changes

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.

  1. 3d ago First seen · 96 lines · 33 tokens per session scan B b014837788dc

Subscribe to this mod's changes

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.

Related

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.

sebastienrousseau/dotfiles · 88 tokens

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…

sebastienrousseau/dotfiles · 137 tokens

aiq-research

Use when asked to run deep research or AI-Q research through a reachable NVIDIA AI-Q Blueprint backend.

laurigates/dotfiles · 25 tokens

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.

laurigates/dotfiles · 49 tokens

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…

laurigates/dotfiles · 117 tokens

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…

laurigates/dotfiles · 88 tokens