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 MadAppGang/claude-code --skill state-machinegit clone --depth 1 https://github.com/MadAppGang/claude-codeWrote 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/madappgang/claude-code/state-machine)<a href="https://agentmods.dev/skills/madappgang/claude-code/state-machine"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/state-machine/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/madappgang/claude-code/state-machine"><img src="https://agentmods.dev/badge/skills/madappgang/claude-code/state-machine.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00020 | $0.01613 |
| Opus 5.5 | $0.00008 | $0.00645 |
| Sonnet 5.5 | $0.00004 | $0.00323 |
| Haiku 4.5 | $0.00002 | $0.00161 |
Grade A, and why
state-machine 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 1mo 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 — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.
plugin: autopilot updated: 2026-01-20
Task Lifecycle State Machine
Version: 0.1.0 Purpose: Manage task state transitions with validation gates Status: Phase 1
When to Use
Use this skill when you need to:
- Understand valid state transitions for tasks
- Implement validation gates before state changes
- Handle iteration loops (In Review -> In Progress)
- Manage escalation to blocked state
- Enforce iteration limits
States
Todo ──→ In Progress ──→ In Review ──→ Done
↑ │
└───────────┘
(iteration)
In Progress ──→ Blocked (escalation)
State Definitions
| State | Description | Entry Condition |
|---|---|---|
| Todo | Task queued for execution | Created with @autopilot label |
| In Progress | Task being executed | Passed start gate |
| In Review | Awaiting validation | Proof generated |
| Done | Task completed | Auto-approved or user approved |
| Blocked | Cannot proceed | Dependency issue or escalation |
Transition Triggers
| From | To | Trigger | Gate |
|---|---|---|---|
| Todo | In Progress | Label @autopilot added | Has acceptance criteria |
| In Progress | In Review | Work complete | Proof >= 80% confidence |
| In Review | Done | Confidence >= 95% | Auto-approval |
| In Review | Done | User approves | User feedback = APPROVAL |
| In Review | In Progress | Confidence < 80% | Validation failed |
| In Review | In Progress | User requests changes | Feedback = REQUESTED_CHANGES |
| In Progress | Blocked | Max iterations | Escalation |
| * | Blocked | Unresolvable blocker | Manual trigger |
Validation Gates
Gate 1: Start Work (Todo -> In Progress)
async function canStartWork(issue: Issue): Promise<boolean> {
const checks = [
// Has acceptance criteria
extractAcceptanceCriteria(issue.description).length > 0,
// No blocking dependencies
(await getBlockingIssues(issue)).length === 0,
// Assigned to autopilot
issue.assignee?.id === AUTOPILOT_BOT_USER_ID,
];
return checks.every(c => c);
}
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.
- 1mo ago First seen · 242 lines · 20 tokens per session scan A e4361f050bc0
state-machine is a skill published in the GitHub repository MadAppGang/claude-code (287 stars, last pushed 7mo ago), licensed MIT. It adds 20 tokens to every session and 1,613 once invoked, about $0.0001 per session on Opus 5.5. 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
animation-blueprint
Navigate, inspect, and author Animation Blueprints — state machines, states, transitions, and transition rules (AnimGraphService). Use when the user asks to create or edit an Animation Blueprint/AnimBP, add a state machine or states, wire transitions between states, set a state's animation, or inspect AnimGraph…
agent-whole-qa
A coordinator for testing an entire application and sending failures to separate development and testing agents. It repeats repair and regression rounds rather than writing code or tests itself.
agent-mvp
An execution workflow for building a minimum viable product, meaning the smallest complete version of a product that can be tested with users. It reads approved plans, assigns development and testing in order, and coordinates fixes until the planned checks pass.
plan-mvp
A planning workflow for defining a complete minimum viable product from the beginning. It gathers decisions in planning mode and records the product, interface, project, data, and API documents for a later implementation workflow.
agent-feature
An execution workflow for implementing a previously planned feature. It reads the approved requirements and coordinates development, testing, and targeted rechecks without redesigning the feature.
plan-feature
A guided planning workflow for adding an incremental feature to an existing product. It compares the requested change with current code and documented requirements before recording the work for implementation.