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.
npx agentmods add skills/prowler-cloud/prowler/skill-syncnpx skills add prowler-cloud/prowler --skill skill-syncgit clone --depth 1 https://github.com/prowler-cloud/prowlerWhat 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 | $0.00058 | $0.00783 |
| Opus 5 | $0.00029 | $0.00392 |
| Sonnet 5 | $0.00012 | $0.00157 |
| Haiku 4.5 | $0.00006 | $0.00078 |
Grade A, and why
skill-sync 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Purpose
Keeps AGENTS.md Auto-invoke sections in sync with skill metadata. When you create or modify a skill, run the sync script to automatically update all affected AGENTS.md files.
Required Skill Metadata
Each skill that should appear in Auto-invoke sections needs these fields in metadata.
auto_invoke can be either a single string or a list of actions:
metadata:
author: prowler-cloud
version: "1.0"
scope: [ui] # Which AGENTS.md: ui, api, sdk, root
# Option A: single action
auto_invoke: "Creating/modifying components"
# Option B: multiple actions
# auto_invoke:
# - "Creating/modifying components"
# - "Refactoring component folder placement"
Scope Values
| Scope | Updates |
|---|---|
root |
AGENTS.md (repo root) |
ui |
ui/AGENTS.md |
api |
api/AGENTS.md |
sdk |
prowler/AGENTS.md |
mcp_server |
mcp_server/AGENTS.md |
Skills can have multiple scopes: scope: [ui, api]
Usage
After Creating/Modifying a Skill
./skills/skill-sync/assets/sync.sh
What It Does
- Reads all
skills/*/SKILL.mdfiles - Extracts
metadata.scopeandmetadata.auto_invoke - Generates Auto-invoke tables for each AGENTS.md
- Updates the
### Auto-invoke Skillssection in each file
Example
Given this skill metadata:
# skills/prowler-ui/SKILL.md
metadata:
author: prowler-cloud
version: "1.0"
scope: [ui]
auto_invoke: "Creating/modifying React components"
The sync script generates in ui/AGENTS.md:
### Auto-invoke Skills
When performing these actions, ALWAYS invoke the corresponding skill FIRST:
| Action | Skill |
|--------|-------|
| Creating/modifying React components | `prowler-ui` |
Commands
# Sync all AGENTS.md files
./skills/skill-sync/assets/sync.sh
# Dry run (show what would change)
./skills/skill-sync/assets/sync.sh --dry-run
# Sync specific scope only
./skills/skill-sync/assets/sync.sh --scope ui
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.
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.
- 2d ago First seen · 122 lines · 58 tokens per session scan A 5c5bcf18cd68
skill-sync is a skill published in the GitHub repository prowler-cloud/prowler (14,736 stars, last pushed today), licensed Apache-2.0. It adds 58 tokens to every session and 783 once invoked, about $0.0003 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.
Other skills, from other repositories
agent-squad-python
Use when building or modifying a Python app that uses the agent-squad Python package — async multi-agent orchestration for Python 3.11+: orchestrator, agents (BedrockLLMAgent, AnthropicAgent, OpenAIAgent, SupervisorAgent, GroundedAgent, ChainAgent, and more), classifier routing (Bedrock, Anthropic, OpenAI), storage…
agent-squad-typescript
Use when building or modifying a Node.js / TypeScript app that uses the agent-squad npm package — multi-agent orchestration: orchestrator, agents (all built-in types + GroundedAgent), classifier routing (Bedrock / Anthropic / OpenAI), storage (in-memory / DynamoDB / SQL), retrievers (Amazon KB / Dakera), and tools…
ak-dev-architecture
Agent Kernel architectural principles, core abstractions, and design patterns. Use this skill when you need to understand the codebase structure, how components interact, or before making changes to core functionality. Covers Session, Agent, Runner, Module, Runtime, AgentService, ChatService (execution core +…
ak-add-capabilities
Add capabilities to an existing Agent Kernel project. This skill guides you through adding guardrails, tracing/observability, session persistence, knowledge bases, MCP server, A2A server, AG-UI server, pre/post hooks, multimodal support, conversation thread support, scheduled tasks (deferred and recurring chat…
ak-dev-new-framework-integration
Step-by-step guide for adding a new agent framework adapter to Agent Kernel. Use this skill when you need to integrate a new agent framework (beyond OpenAI, CrewAI, LangGraph, Google ADK, Smolagents, Pydantic AI). Covers creating the adapter module, implementing Agent/Runner/Module subclasses, adding optional…
ak-build
Add tools, agents, and handoffs to an existing Agent Kernel project. This skill guides you through reading the current project, understanding its framework and structure, then making context-aware additions — new tools, new agents, agent-to-agent handoffs, and Module wiring. The workhorse skill for iterative agent…