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 skills add VoDaiLocz/kilo-kit-mcp --skill workflow-state-machinesgit clone --depth 1 https://github.com/VoDaiLocz/kilo-kit-mcpWrote 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.
[](https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/workflow-state-machines)<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/workflow-state-machines"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/workflow-state-machines/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.
<a href="https://agentmods.dev/skills/vodailocz/kilo-kit-mcp/workflow-state-machines"><img src="https://agentmods.dev/badge/skills/vodailocz/kilo-kit-mcp/workflow-state-machines.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Memory Poisoning · line 31 Skill manipulates agent memory, state, or stored context. Memory corruption can alter personality, override safety rules, or cause unpredictable behavior.Fix: Protect agent memory and state from modification by untrusted content. Use read-only memory for critical instructions and validate all state changes.
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 5.1 | $0.00046 | $0.00857 |
| Opus 5 | $0.00023 | $0.00428 |
| Sonnet 5 | $0.00009 | $0.00171 |
| Haiku 4.5 | $0.00005 | $0.00086 |
Grade A, and why
workflow-state-machines 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.
How it starts
The opening of the file, as written. The whole thing — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Workflow State Machines
Overview
This skill provides a structured framework for building resilient, predictable agentic workflows using directed graph-based state machines. It emphasizes durable execution, explicit state transitions, and auditability to ensure complex agent interactions remain stable and debuggable.
When To Use
- When orchestrating multi-step, multi-agent processes that require durability and fault tolerance.
- When you need to integrate human-in-the-loop (HITL) checkpoints into long-running tasks.
- When debugging non-deterministic agent behavior through state history inspection.
- When enforcing KILO-KIT C4 Runtime Protocol stages as formal state transitions.
Core Concepts
Directed Graph Topologies
- Nodes: Represent distinct agent actions, tool executions, or decision points.
- Edges: Define the transition logic based on input, output, or conditions.
- Immutable State: Workflow state is treated as immutable, with transitions resulting in new state snapshots to ensure clean history.
Durable Execution & Checkpointing
- Workflows automatically persist the state after every transition.
- Resumption: Failed workflows can resume precisely from the last successful node (checkpoint) without re-executing completed prior computations.
Human-in-the-Loop (HITL) Interrupts
- Pause States: Workflows can enter a suspended state to await external input, human approval, or parameter adjustments.
- Manual Overrides: Operators can inject or edit state data while the workflow is paused before triggering the next transition.
Time-Travel Debugging
- All state changes are logged as events in a durable store.
- Replay: Developers can isolate a failing branch, modify inputs, and re-execute that specific subgraph to verify fixes without running the entire workflow from scratch.
Workflow
- Define State Schema: Identify all necessary data attributes required for the entire lifecycle.
- Decompose into Nodes: Break down the process into atomic, idempotent functions.
- Map Edges: Implement conditional routing logic (e.g., success paths, failure paths, human-approval branches).
- Configure Persistence: Set up a store for state snapshots and execution history.
- Implement HITL Points: Add explicit breakpoints where the workflow yields control to the user.
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.
- 12d ago First seen · 69 lines · 46 tokens per session scan A e4a2724e13a2
workflow-state-machines is a skill published in the GitHub repository VoDaiLocz/kilo-kit-mcp (26 stars, last pushed 4d ago), licensed Apache-2.0. It adds 46 tokens to every session and 857 once invoked, about $0.0002 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
llm-structured-output
Get reliable JSON, enums, and typed objects from LLMs using responseformat, tooluse, and schema-constrained decoding across OpenAI, Anthropic, and Google APIs.
drizzle-orm-expert
Expert in Drizzle ORM for TypeScript — schema design, relational queries, migrations, and serverless database integration. Use when building type-safe database layers with Drizzle.
landing-page-generator
Generates high-converting Next.js/React landing pages with Tailwind CSS. Uses PAS, AIDA, and BAB frameworks for optimized copy/components (Heroes, Features, Pricing). Focuses on Core Web Vitals/SEO.
tdmcp-pipeline
Orchestrates the tdmcp feature team end-to-end: design/wireframe → build → integrate → QA → release. Use whenever the user wants to build, implement, develop, ship, or add one or more tdmcp features/tools/effects/controls/AI-prompts for TouchDesigner, or to run them through a coordinated design→develop→QA→deploy…
startcycle-graph-user
Use when a task needs a small, throwaway multi-agent fan-out (a couple of parallel workers plus a review pass) in ANY project, without the full /startcycle-graph contract — no .agents/graph.md bootstrap, no state.json schema, no persistent files. Model-tiered by role (opus plan, sonnet review, haiku or an external CLI…
memb-skill
BDB local-first long-term memory engine (memB). Use when querying, remembering, or adapting preferences, code architectures, and developer patterns across tasks.