agent-skills

agent-skills is a skill for Claude Code, Codex from fmind/dot. It costs 38 tokens per session (1,120 once invoked), scanned B, original, MIT.

A toolkit for creating, checking, publishing, and installing SKILL.md packages for coding agents. These packages contain instructions and related resources that agents can use for specific tasks.

In plain words
What is it for?
Use it to scaffold a skill, organize its files, validate it in isolation, publish it, and install it from a compatible catalog or repository.
Why use it?
It provides a defined package structure and validation process, making skills easier to install and share across different coding-agent tools.

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

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/dot/agent-skills.svg)](https://agentmods.dev/skills/fmind/dot/agent-skills)
Your own site
<a href="https://agentmods.dev/skills/fmind/dot/agent-skills"><img src="https://agentmods.dev/badge/skills/fmind/dot/agent-skills.svg" alt="Measured on agentmods" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,120 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 $0.00038 $0.01120
Opus 5 $0.00019 $0.00560
Sonnet 5 $0.00008 $0.00224
Haiku 4.5 $0.00004 $0.00112

Measured today against content hash 9cca997e1d95, 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 today.

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.

- **Antigravity paths**: `~/.gemini/config/skills` is the shared global path; the CLI-only `~/.gemini/antigravity-cli/skills` creates stale copies, so keep one.
skills/agent-skills/SKILL.md · 66 lines

How it starts

The opening of the file, as written. The whole thing — 66 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, Claude Code, Codex, Copilot, Grok, and OpenCode. skillify owns extracting a skill from a session; skill-security-review owns the trust review of third-party packages.

Author

  1. Scaffold: skills init <name>; the directory name and the lowercase hyphenated frontmatter name stay identical, and the description is one sentence stating capability then trigger, never a workflow summary.
  2. Package: keep SKILL.md focused; scripts, references, and templates live one level deep and are linked directly from SKILL.md per the package rules.
  3. Fit the catalog: read neighbors with overlapping descriptions and link them instead of copying; a first-party skill also declares its CLI names in skills/contracts.json.

Validate

  1. Isolate the candidate: copy only the skill to <candidate-root>/<slug>/SKILL.md with its linked resources; the publisher takes the parent root, and catalog-relative sibling links do not survive a standalone install.
  2. Dry run (proves Agent Skills compatibility, not safety):
    gh skill publish --dry-run <candidate-root>
    
  3. Catalog gate: a first-party skill also passes mise run check:skills and mise run test (contracts, links, routing probes).
  4. Host discovery: inspect whether the skill name and full description survive each host's metadata budget with the read-only listing commands in host discovery; front-load routing cues and record any truncation, because a listed skill is not proof it is followed.

Publish

  1. Authority: gh skill publish adds a topic, a tag, and a GitHub release, so obtain explicit publication authorization for the exact repository, candidate root, and version, then confirm the intended commit and rerun the dry run.
  2. Publish once, stopping on any partial failure instead of retrying with another tag:
    gh skill publish <candidate-root> --tag <vX.Y.Z>
    
  3. Receipt: record repository, commit, tag, and release URL; without the remote receipt the package is validated, not published.

Read the full file on GitHub · 66 lines

Files

What ships with it

3 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. today Changed 9cca997e1d95
  2. yesterday First seen · 66 lines · 38 tokens per session scan B 4cdc1867bc58

Subscribe to this mod's changes

agent-skills is a skill published in the GitHub repository fmind/dot (4 stars, last pushed today), licensed MIT. It adds 38 tokens to every session and 1,120 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.