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 sago-cream/human-out-of-loop --skill prgit clone --depth 1 https://github.com/sago-cream/human-out-of-loopWrote 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/sago-cream/human-out-of-loop/pr)<a href="https://agentmods.dev/skills/sago-cream/human-out-of-loop/pr"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/pr/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/sago-cream/human-out-of-loop/pr"><img src="https://agentmods.dev/badge/skills/sago-cream/human-out-of-loop/pr.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 | $0.00042 | $0.00964 |
| Opus 5.5 | $0.00017 | $0.00386 |
| Sonnet 5.5 | $0.00008 | $0.00193 |
| Haiku 4.5 | $0.00004 | $0.00096 |
Grade A, and why
pr 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 1mo 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 — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Preflight
- Treat the current branch's Git remote as the sole publication target. Never infer a repository from GitHub CLI context, follow a parent/upstream repository, create or synchronize a fork, or publish anywhere else. Require authenticated write access; otherwise stop and ask the user to run from a branch whose remote is their writable fork or repository.
- Run the bundled
bash scripts/pr-preflightfrom the target worktree before review and again before publication. Never review or publish while blocked. - Inspect its prospective commits and complete diff for task scope.
- If the branch is default or spent, rebuild from the reported base with only intended commits, then rerun preflight.
- If base or head changes, repeat the affected review.
Review
- Use the preflight base and head; verify worktree HEAD before each review.
- Review the complete
base...headdiff. Report actionable findings and stop. Run repository checks with CI-equivalent options; expected visual changes need scoped assertions, not blanket bypasses. - For every UI change, reuse supplied media or capture matched, reproducible before/after media from base and head. Capture
Beforefrom the exact base commit the PR will merge into andAfterfrom the reviewed head. On follow-ups, reuse or recaptureBeforefrom that base; never use an earlier feature-branch revision or a priorAfteras the newBefore:- Use video for interaction, motion, or multiple steps; images otherwise. Keep recordings focused and paced for a reviewer, and inspect the exported media before publication.
- Match viewport, state, data, and action sequence; verify each capture runs the intended revision's build.
- Frame screenshots with enough surrounding UI to make the changed element's location and purpose clear, including a page or section landmark and relevant adjacent controls. Prefer viewport- or section-level framing; use tight element crops only when context is genuinely unnecessary.
- Keep media untracked through
.git/info/exclude. - Never publish with either side missing.
What ships with it
4 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.
- 1mo ago Changed · +4 lines d481ff9aeb2f
- 2mo ago First seen · 46 lines · 42 tokens per session scan A e14cb7736bc3
pr is a skill published in the GitHub repository sago-cream/human-out-of-loop (6 stars, last pushed 1mo ago), licensed MIT. It adds 42 tokens to every session and 964 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
merge-batch
Prepare and merge an owner-selected PR batch with contributor credit and exact-candidate admission. Use for a pasted PR list; combined focused validation is diagnostic, and every actual landing still requires its applicable checks and authorization.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…