skill-activation-patterns

skill-activation-patterns is a skill for Claude Code from latestaiagents/agent-skills. It costs 99 tokens per session (1,502 once invoked), scanned A, original, MIT.

A guide to designing and troubleshooting the rules that decide when an agent skill activates. It explains how to avoid skills firing for unrelated requests or missing relevant ones.

In plain words
What is it for?
Use it when creating a group of related skills, resolving overlapping triggers, or diagnosing why a skill activates too often or not at all.
Why use it?
It helps reduce noisy activations and prevent useful skills from staying silent when several skills have similar purposes.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the skills-authoring plugin — 4 skills shipped together , and of latestaiagents

Good fit Use it when creating a group of related skills, resolving overlapping triggers…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/latestaiagents/agent-skills/skill-activation-patterns
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.

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

Made for: Claude Code.

Or install skills-authoring, the plugin that ships this one along with the rest of its 4 skills.

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 skill-activation-patterns

README.md
[![agentmods](https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-activation-patterns.svg)](https://agentmods.dev/skills/latestaiagents/agent-skills/skill-activation-patterns)
Your own site
<a href="https://agentmods.dev/skills/latestaiagents/agent-skills/skill-activation-patterns"><img src="https://agentmods.dev/badge/skills/latestaiagents/agent-skills/skill-activation-patterns.svg" alt="Measured on agentmods" height="20"></a>
Per session 99 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,502 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00099 $0.01502
Opus 5 $0.00049 $0.00751
Sonnet 5 $0.00020 $0.00300
Haiku 4.5 $0.00010 $0.00150

Measured 3d ago against content hash 1805e7add5d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

skill-activation-patterns 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 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.

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/skills-authoring/skill-activation-patterns/SKILL.md · 184 lines

How it starts

The opening of the file, as written. The whole thing — 184 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Skill Activation Patterns

A skill that fires at the wrong time is as useless as one that never fires. Design activation like you'd design a cron expression: specific, testable, boundaried.

When to Use

  • Debugging skills that don't fire
  • Two skills claiming the same trigger
  • Skills firing on unrelated queries
  • Designing a new suite with multiple related skills

The Activation Signal Stack

The model matches your skill against user queries using:

  1. Name — weak signal
  2. Description first sentence — strong signal, this is the "what"
  3. "Use this skill when" line — strongest signal, the "when"
  4. "Activate when" keyword list — pattern match against query phrases

Invest most in (3) and (4).

Four Activation Patterns

1. Error-Driven

Skill fires when user pastes or describes an error:

description: |
  Decode Java stack traces and suggest root causes.
  Use this skill when user shares a stack trace, exception, or runtime error in Java.
  Activate when: Exception, NullPointerException, stack trace, Caused by, Java error, runtime crash.

Include the literal tokens that appear in errors. Users paste them verbatim.

2. Intent-Driven

Skill fires when user expresses a goal:

description: |
  Refactor code to extract methods, rename, and improve structure without changing behavior.
  Use this skill when user asks to refactor, clean up, or restructure existing code.
  Activate when: refactor, clean up, extract method, rename, restructure, DRY up, improve this code.

Match imperative verbs and goal phrases.

3. Tool/Technology-Driven

Skill fires when the user mentions a specific tool:

description: |
  Configure Next.js App Router — server components, server actions, middleware, caching.
  Use this skill when the user is working with Next.js App Router, specifically app/ directory routes.
  Activate when: Next.js, App Router, server component, server action, app/ directory, use server.

Name the technology and its key concepts; matches work well.

Read the full file on GitHub · 184 lines

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 · 184 lines · 99 tokens per session scan A 1805e7add5d5

Subscribe to this mod's changes

skill-activation-patterns is a skill published in the GitHub repository latestaiagents/agent-skills (5 stars, last pushed 4mo ago), licensed MIT. It adds 99 tokens to every session and 1,502 once invoked, about $0.0005 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 2026-09-03.