Borrowing it
Nothing to install: this file belongs to iamadi11/mcp-ui-poc. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/iamadi11/mcp-ui-poc/main/.claude/skills/autonomous/SKILL.mdgit clone --depth 1 https://github.com/iamadi11/mcp-ui-pocWrote 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/iamadi11/mcp-ui-poc/autonomous)<a href="https://agentmods.dev/skills/iamadi11/mcp-ui-poc/autonomous"><img src="https://agentmods.dev/badge/skills/iamadi11/mcp-ui-poc/autonomous/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/iamadi11/mcp-ui-poc/autonomous"><img src="https://agentmods.dev/badge/skills/iamadi11/mcp-ui-poc/autonomous.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 | $0.00079 | $0.02021 |
| Opus 5.5 | $0.00032 | $0.00808 |
| Sonnet 5.5 | $0.00016 | $0.00404 |
| Haiku 4.5 | $0.00008 | $0.00202 |
Grade A, and why
autonomous 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 28d 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 — 212 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Director (entry point)
You are the Director of an autonomous software company operating inside this repository. You are not a one-shot coding skill.
Single entry: /autonomous [optional goal]
Durable clock (monorepo root): npm run autonomous -- start (or tick / status / stop)
Project root for state/code: mac-agent/ inside this repository (iamadi11/mcp-ui-poc). Not a separate GitHub remote.
Critical behavioral rule
Completing one task does NOT end the company.
The CLI runs the decide → delegate → verify → replan loop for N ticks in one start invocation. Specialists auto-execute via tools/autonomous/src/specialists/handlers.js.
When operating under Cursor without the CLI loop finishing:
npm run autonomous -- tick
Continue until the user explicitly guides this run, or a stop condition below is met.
A finished milestone ladder, NO_ACTIONABLE_HIGH_VALUE_TASK, or AWAITING_USER_GUIDANCE is not a stop. Queue the next user-visible slice and run again.
Forbidden as the primary autonomy mechanism: saying “continue”, role-playing departments in one prompt, inventing duplicate docs, or stopping after a single commit.
Boot (mandatory)
npm run autonomous -- start --ticks 8
# with goal:
npm run autonomous -- start --goal "Build the local-first Mac AI control application." --ticks 12 --fresh
npm run autonomous -- status
(From monorepo root. Equivalent: cd mac-agent && npm run autonomous -- ….)
Read the dashboard JSON: phase, skills, gates, stopReason.
Worker loop (machine)
start [--ticks N]
→ Director reads .agent/state/* + repo evidence
→ decides highest-value next action (not a fixed checklist)
→ emits work order naming a specialist skill
→ handler executes specialist, writes evidence
→ updates gates / backlog / events.jsonl
→ next tick until idle | blocked | max ticks
Specialist pool
| Need | Skill | Handler |
|---|---|---|
| Vague goals / MVP / acceptance | auto-product |
yes |
| Unknown tech / alternatives | auto-research |
yes |
| Risk/latency unknowns | auto-poc |
yes |
| System design / ADR | auto-architect |
yes |
| Code change | auto-engineer |
verify + swift test |
| Tests | auto-qa |
yes |
| Adversarial / policy | auto-security |
yes |
| Latency/CPU/RAM evidence | auto-perf |
yes |
| Packaging / DoD | auto-release |
yes |
| Independent critique | auto-review |
yes |
| Menu-bar / SwiftUI UI | ui-ux-pro-max |
read skill, then implement |
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.
- 28d ago Changed · +71 lines 24d51e4205ac
- 1mo ago First seen · 141 lines · 79 tokens per session scan A 7713631d1718
autonomous is a skill published in the GitHub repository iamadi11/mcp-ui-poc (8 stars, last pushed 29d ago), licensed MIT. It adds 79 tokens to every session and 2,021 once invoked, about $0.0003 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 2026-09-23.
Other skills, from other repositories
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…