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 patleeman/neon-pilot --skill auto-modegit clone --depth 1 https://github.com/patleeman/neon-pilotWrote 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/patleeman/neon-pilot/auto-mode)<a href="https://agentmods.dev/skills/patleeman/neon-pilot/auto-mode"><img src="https://agentmods.dev/badge/skills/patleeman/neon-pilot/auto-mode.svg" alt="Measured on agentmods" 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 | $0.00034 | $0.00504 |
| Opus 5 | $0.00017 | $0.00252 |
| Sonnet 5 | $0.00007 | $0.00101 |
| Haiku 4.5 | $0.00003 | $0.00050 |
Grade A, and why
goal-mode 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 7d 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 — 41 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Goal Mode
Use this skill when you have a sustained objective that may span multiple turns.
Goal mode is a single active objective. The system injects the current objective into continuation turns and automatically schedules another turn while the goal is active.
How it works
goal(objective: "...")— enable goal mode or replace the active objective.goal(status: "pause")— pause the active objective without losing it.goal(status: "resume")— resume a paused objective.goal(status: "complete")— disable goal mode when the objective is met.
The system automatically schedules a visible goal-continuation block after each turn while the goal is active, then uses it to trigger the next turn.
Rules
- Do not create a goal for every ordinary request — only for sustained multi-turn tasks.
- Calling
goalwith an objective while goal mode is active replaces the objective and keeps goal mode running. - If the goal needs to wait, schedule a
conversationdeferred resume, then callgoalwithstatus: "pause". Include instructions in the deferred resume prompt to callgoalwithstatus: "resume"when work should continue. - Mark the goal complete with
goal { status: "complete" }only when the objective is actually achieved. - The system's continuation prompt already includes the current objective.
Safety guards
If goal-mode turns produce no tool calls for two consecutive turns, goal mode is disabled with stopReason: "no progress" so it cannot spin forever. Starting, updating, or completing a goal resets this.
Queued continuations are cancelled or ignored when the goal changes or completes, and duplicate completion calls are treated as no-ops. Completing a goal does not abort the current turn; it prevents the agent-end scheduler from queuing another continuation. Turn-end events only update progress counters, so tool-heavy runs cannot stack stale continuations before completion. Goal mode should end quietly once the objective is complete.
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.
- 7d ago First seen · 41 lines · 34 tokens per session scan A 22ce18e4ee26
goal-mode is a skill published in the GitHub repository patleeman/neon-pilot (23 stars, last pushed 1mo ago), licensed MIT. It adds 34 tokens to every session and 504 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
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…