advisor-triggers

advisor-triggers is a skill for Claude Code, Codex from majiayu000/claude-skill-registry. It costs 17 tokens per session (1,874 once invoked), scanned A, original, MIT.

A skill that detects requests where critical analysis may be useful and suggests an /advise command. Its listed examples include adding dependencies, changing architecture, and expanding scope.

In plain words
What is it for?
Use it to identify requests involving new packages or services, architecture changes such as microservices or monorepos, and significant feature expansions.
Why use it?
It helps surface trade-offs before changes that could increase complexity or affect many parts of a project.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to identify requests involving new packages or services, architecture changes such as microservices or monorepos, and significant feature expansions.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/majiayu000/claude-skill-registry/advisor-triggers
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 majiayu000/claude-skill-registry --skill advisor-triggers
Clone the repo
git clone --depth 1 https://github.com/majiayu000/claude-skill-registry

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 advisor-triggers

README.md
[![agentmods](https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/advisor-triggers/github.svg)](https://agentmods.dev/skills/majiayu000/claude-skill-registry/advisor-triggers)
Your own site
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/advisor-triggers"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/advisor-triggers/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for advisor-triggers

Your own site · 80×15
<a href="https://agentmods.dev/skills/majiayu000/claude-skill-registry/advisor-triggers"><img src="https://agentmods.dev/badge/skills/majiayu000/claude-skill-registry/advisor-triggers.svg" alt="Reviewed on agentmods" width="80" 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 1,874 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00017 $0.01874
Opus 5 $0.00009 $0.00937
Sonnet 5 $0.00003 $0.00375
Haiku 4.5 $0.00002 $0.00187

Measured 12d ago against content hash bf6d24d017e0, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

advisor-triggers 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 12d 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/agent/advisor-triggers/SKILL.md · 361 lines

How it starts

The opening of the file, as written. The whole thing — 361 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Advisor Auto-Invoke Triggers

Purpose

Detect patterns in user requests that indicate a need for critical thinking analysis. Suggests running /advise when users propose significant changes without first considering trade-offs.

Detection Patterns

Pattern 1: New Dependencies

Triggers:

  • "add [package/library/service]"
  • "use [technology]"
  • "integrate [external service]"
  • "switch to [different tool]"

Examples:

  • "Let's add Redis for caching"
  • "Use TensorFlow for ML"
  • "Integrate Stripe for payments"
  • "Switch to PostgreSQL"

Why advise? New dependencies increase complexity and maintenance burden.

Pattern 2: Architecture Changes

Triggers:

  • "refactor to [pattern]"
  • "restructure as [architecture]"
  • "migrate to [architecture]"
  • "convert to [pattern]"

Examples:

  • "Refactor to microservices"
  • "Restructure as event-driven"
  • "Migrate to serverless"
  • "Convert to monorepo"

Why advise? Architectural changes have far-reaching implications.

Pattern 3: Scope Expansions

Triggers:

  • "also add [feature]"
  • "extend to [capability]"
  • "support [new use case]"
  • "make it [do more]"

Examples:

  • "Also add real-time collaboration"
  • "Extend to mobile platforms"
  • "Support multi-tenancy"
  • "Make it work offline"

Why advise? Scope creep can derail projects.

Pattern 4: Technology Replacements

Triggers:

  • "[X] instead of [Y]"
  • "replace [X] with [Y]"
  • "swap [X] for [Y]"

Examples:

  • "GraphQL instead of REST"
  • "Replace Express with Fastify"
  • "Swap MySQL for MongoDB"

Why advise? Tech replacements have migration costs.

Pattern 5: Scale Changes

Triggers:

  • "handle [large number]"
  • "scale to [big metric]"
  • "support [many users]"

Examples:

  • "Handle 1M requests/day"
  • "Scale to 100K users"
  • "Support 10K concurrent"

Why advise? Premature optimization is common.

Detection Logic

function shouldInvokeAdvisor(userRequest: string): boolean {
  const triggers = [
    // Dependencies
    /add (redis|mongodb|postgres|graphql|webpack|docker)/i,
    /use (tensorflow|pytorch|react|vue|angular)/i,
    /integrate (stripe|auth0|sendgrid|aws)/i,
    /switch to (typescript|rust|go|kubernetes)/i,

    // Architecture
    /refactor to (microservices|serverless|event-driven)/i,
    /restructure as/i,
    /migrate to/i,
    /convert to/i,

    // Scope
    /also add/i,
    /extend to/i,
    /support (mobile|multi-tenant|real-time|offline)/i,

    // Technology replacement
    /instead of/i,
    /replace \w+ with/i,
    /swap \w+ for/i,

    // Scale
    /scale to/i,
    /handle \d+[kmb]/i, // 1k, 1m, 1b
    /support \d+k/i,
  ];

  return triggers.some((pattern) => pattern.test(userRequest));
}

Read the full file on GitHub · 361 lines

Files

What ships with it

1 file 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. 12d ago First seen · 361 lines · 17 tokens per session scan A bf6d24d017e0

Subscribe to this mod's changes

advisor-triggers is a skill published in the GitHub repository majiayu000/claude-skill-registry (600 stars, last pushed yesterday), licensed MIT. It adds 17 tokens to every session and 1,874 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 2026-08-30.