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 kwannoel/the-controller --skill the-controller-autonomous-executiongit clone --depth 1 https://github.com/kwannoel/the-controllerWrote 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/kwannoel/the-controller/the-controller-autonomous-execution)<a href="https://agentmods.dev/skills/kwannoel/the-controller/the-controller-autonomous-execution"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/the-controller-autonomous-execution/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/kwannoel/the-controller/the-controller-autonomous-execution"><img src="https://agentmods.dev/badge/skills/kwannoel/the-controller/the-controller-autonomous-execution.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 | $0.00019 | $0.01702 |
| Opus 5.5 | $0.00008 | $0.00681 |
| Sonnet 5 | $0.00004 | $0.00340 |
| Haiku 4.5 | $0.00002 | $0.00170 |
Grade A, and why
the-controller-autonomous-execution 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 yesterday.
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 — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomous Execution
Execute an implementation plan end-to-end with zero human interaction. Same quality gates as subagent-driven-development (fresh subagent per task, spec review, code quality review, final review), but the orchestrator handles all decisions autonomously.
Core principle: Full subagent-driven-development quality, zero human checkpoints — orchestrator resolves ambiguity from plan context, only surfaces when genuinely blocked.
Announce at start: "I'm using the the-controller-autonomous-execution skill to execute this plan autonomously. I'll report back when all tasks are complete."
When to Use
digraph when_to_use {
"Have implementation plan?" [shape=diamond];
"Want fully autonomous execution?" [shape=diamond];
"the-controller-autonomous-execution" [shape=box];
"the-controller-subagent-driven-development" [shape=box];
"Use the-controller-writing-plans first" [shape=box];
"Have implementation plan?" -> "Want fully autonomous execution?" [label="yes"];
"Have implementation plan?" -> "Use the-controller-writing-plans first" [label="no"];
"Want fully autonomous execution?" -> "the-controller-autonomous-execution" [label="yes"];
"Want fully autonomous execution?" -> "the-controller-subagent-driven-development" [label="no - want human checkpoints"];
}
vs. subagent-driven-development:
- Same quality gates (implementer + spec review + code quality review + final review)
- Orchestrator answers subagent questions from plan context (no human in loop)
- Includes worktree setup (no separate step needed)
- No merge at end (human reviews and decides)
vs. executing-plans:
- Fresh subagent per task (no context pollution)
- Automated review gates (not human checkpoints)
- Fully autonomous (no "ready for feedback" pauses)
The Process
digraph process {
rankdir=TB;
"Set up worktree (the-controller-using-git-worktrees)" [shape=box];
"Read plan, extract all tasks with full text, create TodoWrite" [shape=box];
subgraph cluster_per_task {
label="Per Task";
"Dispatch implementer subagent" [shape=box];
"Implementer asks questions?" [shape=diamond];
"Orchestrator answers from plan context" [shape=box];
"Orchestrator can answer?" [shape=diamond];
"Surface to human (ONLY blocker case)" [shape=box style=filled fillcolor=lightyellow];
"Implementer implements, tests, commits, self-reviews" [shape=box];
"Dispatch spec reviewer subagent" [shape=box];
"Spec compliant?" [shape=diamond];
"Implementer fixes spec gaps" [shape=box];
"Dispatch code quality reviewer subagent" [shape=box];
"Code quality approved?" [shape=diamond];
"Implementer fixes quality issues" [shape=box];
"Mark task complete" [shape=box];
}
"More tasks?" [shape=diamond];
"Dispatch final code reviewer for entire implementation" [shape=box];
"Report final summary" [shape=box style=filled fillcolor=lightgreen];
"Set up worktree (the-controller-using-git-worktrees)" -> "Read plan, extract all tasks with full text, create TodoWrite";
"Read plan, extract all tasks with full text, create TodoWrite" -> "Dispatch implementer subagent";
"Dispatch implementer subagent" -> "Implementer asks questions?";
"Implementer asks questions?" -> "Orchestrator answers from plan context" [label="yes"];
"Implementer asks questions?" -> "Implementer implements, tests, commits, self-reviews" [label="no"];
"Orchestrator answers from plan context" -> "Orchestrator can answer?";
"Orchestrator can answer?" -> "Dispatch implementer subagent" [label="yes - send answer"];
"Orchestrator can answer?" -> "Surface to human (ONLY blocker case)" [label="no"];
"Surface to human (ONLY blocker case)" -> "Dispatch implementer subagent" [label="human answers"];
"Implementer implements, tests, commits, self-reviews" -> "Dispatch spec reviewer subagent";
"Dispatch spec reviewer subagent" -> "Spec compliant?";
"Spec compliant?" -> "Implementer fixes spec gaps" [label="no"];
"Implementer fixes spec gaps" -> "Dispatch spec reviewer subagent" [label="re-review"];
"Spec compliant?" -> "Dispatch code quality reviewer subagent" [label="yes"];
"Dispatch code quality reviewer subagent" -> "Code quality approved?";
"Code quality approved?" -> "Implementer fixes quality issues" [label="no"];
"Implementer fixes quality issues" -> "Dispatch code quality reviewer subagent" [label="re-review"];
"Code quality approved?" -> "Mark task complete" [label="yes"];
"Mark task complete" -> "More tasks?";
"More tasks?" -> "Dispatch implementer subagent" [label="yes"];
"More tasks?" -> "Dispatch final code reviewer for entire implementation" [label="no"];
"Dispatch final code reviewer for entire implementation" -> "Report final summary";
}
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.
- yesterday First seen · 162 lines · 19 tokens per session scan A 816f1b5c49c5
the-controller-autonomous-execution is a skill published in the GitHub repository kwannoel/the-controller (13 stars, last pushed 4mo ago), licensed MIT. It adds 19 tokens to every session and 1,702 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 2026-09-23.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
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…
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…