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 tomzx/agents --skill improve-autonomygit clone --depth 1 https://github.com/tomzx/agentsWrote 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/tomzx/agents/improve-autonomy)<a href="https://agentmods.dev/skills/tomzx/agents/improve-autonomy"><img src="https://agentmods.dev/badge/skills/tomzx/agents/improve-autonomy/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/tomzx/agents/improve-autonomy"><img src="https://agentmods.dev/badge/skills/tomzx/agents/improve-autonomy.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00067 | $0.02075 |
| Opus 5.5 | $0.00027 | $0.00830 |
| Sonnet 5.5 | $0.00013 | $0.00415 |
| Haiku 4.5 | $0.00007 | $0.00208 |
Grade A, and why
improve-autonomy 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 22d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Improve Autonomy
Asks: "What would have been needed to run this session autonomously, end to end, with no human in the loop?" Produces a structured readiness assessment that lists missing context, missing tools, missing decisions, and missing guardrails that prevented full autonomy.
This is not about incremental automation (see /automate-session for that).
This is about imagining the fully autonomous version of the session and working backward to identify every gap.
Prerequisites
- A session with at least some completed work (conversation history, git changes, or both)
Steps
1. Reconstruct the session as an autonomous pipeline
Build a chronological trace of the session, then rewrite it as if an autonomous agent had performed it. For each step, describe:
- What the agent would need to know before executing it (context, requirements, constraints, preferences)
- What the agent would need to access (files, APIs, databases, environments, tools)
- What the agent would need to decide (priority, scope, trade-offs, style, tone)
- How the agent would know it succeeded (verifiable outcome, acceptance criteria, tests, review)
Sources to draw from:
- Conversation turns: every question asked, answer given, approval granted, or correction made
git log --onelinesince session start- File reads, writes, edits made during the session
- Any external tool calls (GitHub, Slack, etc.)
2. Classify every human input by replaceability
For each instance where the human provided input, classify it:
| Label | Meaning |
|---|---|
| Pre-loaded | Could have been provided upfront in a spec, config file, AGENTS.md rule, or skill instructions. The information is stable, reusable, or project-specific. |
| Derivable | Could have been inferred from available context (codebase state, git history, prior sessions, project conventions). An agent with the right heuristics would have figured it out. |
| Judgment call | Required genuine human judgment (novel trade-off, aesthetic preference, business priority, stakeholder alignment). No reasonable heuristic or prior pattern could replace it. |
| Correction | The human corrected a wrong assumption or output. This reveals a gap in the agent's knowledge or reasoning that must be fixed before autonomy is possible. |
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.
- 22d ago Changed · +10 lines a739d45753e6
- 24d ago Changed 58773b807f04
- 1mo ago First seen · 221 lines · 67 tokens per session scan A e43af2a3c4c1
improve-autonomy is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 67 tokens to every session and 2,075 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 2026-09-03.
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…