A sample skill template with placeholders for when to use a skill, which tools it can call, and how it should behave. It is not a description of a completed capability.

It is for drafting a skill specification with scenarios, tools, workflows, and safety rules.

It provides a structure for documenting or creating a skill, but the supplied text does not identify a real task it performs.

my-skill — Skill for Claude Code and Codex by FoneClaw-AI: A sample skill template with placeholders for when to…

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/foneclaw-ai/foneclaw-android/_template

Any agent

npx skills add FoneClaw-AI/foneclaw-android --skill _template

Clone the repo

git clone --depth 1 https://github.com/FoneClaw-AI/foneclaw-android

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/_template.svg)](https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/_template)

Your own site

<a href="https://agentmods.dev/skills/foneclaw-ai/foneclaw-android/_template"><img src="https://agentmods.dev/badge/skills/foneclaw-ai/foneclaw-android/_template.svg" alt="Measured on agentmods" height="20"></a>

Per session 17 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 413 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. 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.

Model	Per session	Once invoked
Fable 5	$0.00017	$0.00413
Opus 5	$0.00009	$0.00206
Sonnet 5	$0.00003	$0.00083
Haiku 4.5	$0.00002	$0.00041

Measured 4d ago against content hash a43023751804, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

my-skill 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.

skills/_template/SKILL.md · 63 lines

What it actually says

My Skill

Scope / Applicable Scenarios

Use this skill when the user wants to:

Scenario A: what triggers it and what the user expects.
Scenario B: another common trigger.

Do NOT use this skill when:

The task is outside this skill's domain.
Another skill is more appropriate.

Available Tools

tool_name_1: Brief description of what this tool does and its key parameters.
tool_name_2: Brief description.

Recommended Workflows

1. Primary Scenario

Call tool_name_1 with the necessary parameters.
Check the result. If successful, proceed to step 3.
If the result indicates an error, inform the user and suggest next steps.
Call tool_name_2 to complete the task.

2. Alternative Scenario

Ask the user for any missing information (e.g., destination, account name).
Call tool_name_1 with the confirmed parameters.
Present the result clearly to the user.

Rules / Agent Behavior Requirements

Always confirm with the user before performing destructive or high-risk actions.
Never expose sensitive data (passwords, tokens) in responses or tool parameters.
If a tool returns missing permission, guide the user to grant the permission first.
Handle empty results gracefully — explain possible causes rather than stating "nothing found."

Completion Criteria

The task is complete when:

The requested information has been presented to the user.
The requested action has been executed successfully.
The user has been clearly informed of any required manual steps or limitations.

Failure Conditions

Stop and notify the user when:

Required permissions are missing and the user declines to grant them.
A tool fails after a reasonable retry attempt.
The user's request is ambiguous and they cannot provide clarification.

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.

4d ago First seen · 63 lines · 17 tokens per session scan A a43023751804

Subscribe to this mod's changes

my-skill is a skill published in the GitHub repository FoneClaw-AI/foneclaw-android (5 stars, last pushed 2d ago), licensed MIT. It adds 17 tokens to every session and 413 once invoked, about $0.0001 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.

accessibility-service ai-agent ai-agents ai-tools android miclaw

my-skill