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 paulbaranowski/wild-horses --skill autonomousgit clone --depth 1 https://github.com/paulbaranowski/wild-horsesWrote 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/paulbaranowski/wild-horses/autonomous)<a href="https://agentmods.dev/skills/paulbaranowski/wild-horses/autonomous"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/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/paulbaranowski/wild-horses/autonomous"><img src="https://agentmods.dev/badge/skills/paulbaranowski/wild-horses/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 | $0.00199 | $0.03241 |
| Opus 5 | $0.00100 | $0.01621 |
| Sonnet 5 | $0.00040 | $0.00648 |
| Haiku 4.5 | $0.00020 | $0.00324 |
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 10d 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 — 194 lines — stays where its author put it; the contents beside it link to each section on GitHub.
autonomous
Take a task all the way to an opened pull request, with no human in the loop. The task is an issue/ticket link or a plan/spec file. Resolve the task from the link or file. Then run an implement → test → review → PR → tend loop entirely on your own judgment.
Input resolution (the task source)
Resolve the task target in this priority order:
- URL in the arguments. Detect the host and fetch the issue title and body.
- GitHub issue/PR →
gh issue view <url>/gh pr view <url>. - Linear → the
linearCLI if present, otherwise WebFetch. - anything else → WebFetch.
- GitHub issue/PR →
- File path in the arguments. This is a path to a plan, spec, or issue
file. Examples:
~/plans/<repo>/foo.md, or any local.md. Read it with theReadtool. Its full content is the Task. There is no separate "title" to fetch, because the file is the spec. - A task already in the conversation. This is an issue ref or link, or a
plan/spec already read into context.
plan-keeper:plan-dohands off this way: it reads the plan file, then invokes this skill. Use that content as the Task. Do not re-fetch or re-read it. - Nothing resolvable. This is the one allowed stop. It is a precondition failure, not a mid-task clarification. State plainly that the skill needs an issue link or a plan file, then stop. Once a task is resolved and work begins, the "never ask" contract below governs everything.
The fetched issue (title and body) becomes the Task you work from. So does the plan/spec file's content. See the Task section below.
Autonomy
Make every design and implementation decision yourself. Do not stop to ask clarifying questions. Assume no human is watching this session.
No exceptions:
- Don't ask even for "fundamental" or "architectural" decisions.
- Don't ask even for "I just need one quick clarification".
- Don't ask even when the issue description is empty or incomplete. Proceed from the title.
- Don't ask "in the spirit of being efficient".
What ships with it
3 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 10d ago First seen · 194 lines · 199 tokens per session scan A a94596460d9e
autonomous is a skill published in the GitHub repository paulbaranowski/wild-horses (12 stars, last pushed 22d ago), licensed MIT. It adds 199 tokens to every session and 3,241 once invoked, about $0.0010 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
prowler-commit
Creates professional git commits following conventional-commits format. Trigger: When creating commits, after completing code changes, when user asks to commit.
gh-auth-isolation
Safely manage multiple GitHub identities (EMU + personal) in agent workflows.
comet-github
A routing guide for Comet-related GitHub work. It directs requests about pull requests, issues, CI failures, ideas, and fixes to the appropriate review or implementation process.
github-skill
Work with GitHub via the gh CLI — clone repositories, create/list/merge pull requests, create/list issues, and run any other gh command (API calls, workflow runs, releases, repo administration). List operations return parsed JSON.
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
nvca-chart-release
Release NVCA Operator chart changes from the native monorepo source to the vendored Helm chart. Use when updating the vendored NVCA Operator chart, changing NVCA image refs, publishing helm-nvca-operator, or validating the chart against a self-managed control plane.