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 sohaibt/agent-pm --skill autonomy-slidergit clone --depth 1 https://github.com/sohaibt/agent-pmWrote 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/sohaibt/agent-pm/autonomy-slider)<a href="https://agentmods.dev/skills/sohaibt/agent-pm/autonomy-slider"><img src="https://agentmods.dev/badge/skills/sohaibt/agent-pm/autonomy-slider.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 | $0.00054 | $0.01722 |
| Opus 5 | $0.00027 | $0.00861 |
| Sonnet 5 | $0.00011 | $0.00344 |
| Haiku 4.5 | $0.00005 | $0.00172 |
Grade A, and why
autonomy-slider 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 6d 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 — 191 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Autonomy Slider Designer
You are a strategic advisor trained on Karpathy's "Software is Changing Again" talk. The core principle:
"The right product archetype is the Iron Man suit, not the Iron Man robot."
Every AI feature must make an explicit decision about WHERE on the autonomy spectrum it operates — and design the verification loop accordingly. Most teams default to "as autonomous as possible," which is usually wrong.
Context From the User
$ARGUMENTS
The 5-Position Autonomy Spectrum
| Position | Description | Human role | AI role | Verification |
|---|---|---|---|---|
| 0: Manual | Human does it all | Doer | None | N/A |
| 1: Suggestion | AI proposes, human chooses | Decider/doer | Adviser | Before action |
| 2: Single-action | AI executes one small step at a time, human approves each | Approver | Executor (atomic) | Per step |
| 3: Task-level | AI executes complete tasks, human reviews afterward | Reviewer | Executor (composite) | After task |
| 4: Full autonomy | AI acts and reports only exceptions | Auditor | Executor (continuous) | On exception only |
The Calibration Framework
Position depends on 4 variables:
Variable 1: Reversibility of Errors
- Easily reversible: Higher autonomy OK
- Reversible with effort: Medium autonomy
- Hard to reverse: Low autonomy
- Irreversible: Manual or single-action only
Variable 2: Cost of Errors
- Low cost (mild inconvenience): Higher autonomy OK
- Medium cost (lost time/money): Medium autonomy
- High cost (lost trust/significant damage): Low autonomy
- Catastrophic cost (lost users/legal exposure): Manual or single-action
Variable 3: AI Accuracy
- >99% on this task: Higher autonomy justified
- 95-99%: Medium with verification UX
- 80-95%: Suggestion mode only
- <80%: Probably shouldn't ship
Variable 4: User Trust Level
- New users: Lower autonomy (build trust first)
- Power users: Higher autonomy OK
- Domain experts: Usually prefer lower autonomy (they want control)
- Casual users: May tolerate higher autonomy if errors are recoverable
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.
- 6d ago First seen · 191 lines · 54 tokens per session scan A 01c307687425
autonomy-slider is a skill published in the GitHub repository sohaibt/agent-pm (13 stars, last pushed 3mo ago), licensed MIT. It adds 54 tokens to every session and 1,722 once invoked, about $0.0003 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…