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 sumimakito/roll --skill roll-advisorgit clone --depth 1 https://github.com/sumimakito/rollWrote 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/sumimakito/roll/roll-advisor)<a href="https://agentmods.dev/skills/sumimakito/roll/roll-advisor"><img src="https://agentmods.dev/badge/skills/sumimakito/roll/roll-advisor/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/sumimakito/roll/roll-advisor"><img src="https://agentmods.dev/badge/skills/sumimakito/roll/roll-advisor.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 | $0.00032 | $0.00350 |
| Opus 5.5 | $0.00013 | $0.00140 |
| Sonnet 5.5 | $0.00006 | $0.00070 |
| Haiku 4.5 | $0.00003 | $0.00035 |
Grade A, and why
roll-advisor 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 2mo 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.
What it actually says
roll-advisor
Optional, gated advice after roll-resolve. Skip when advisor mode is off.
Use interactive UI for skip/apply choices when available; otherwise ask concise
text questions. Never apply advice without explicit approval.
Invariant: each suggestion must preserve the PR's original behavior and scope. If a suggestion changes what the PR accomplishes, label it goal-altering and require explicit approval before treating it as an option.
Procedure
- Inspect conflicted files, resolved hunks, and history:
git log --oneline -20 -- <file>andgit shortlog -sn -- <file>. - Identify conflict cause: hot file, weak boundary, broad PR, base churn, commit order, strategy mismatch, etc.
- Offer one up-front "ignore / skip all" choice. If chosen, drop all advice for this run.
- Suggest valid conflict-reducing actions: split PR, reorder/squash commits, narrow scope, extract contended code, switch merge/rebase strategy next time, or coordinate around base churn.
- For each suggestion, state how it preserves the original goal.
- Apply only approved suggestions. Otherwise continue with the existing resolution; advice is non-blocking.
Stop Rules
- Do not edit before approval.
- Do not present behavior-changing work as normal advice.
- Do not re-ask after the user skips all advice.
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.
- 2mo ago First seen · 35 lines · 32 tokens per session scan A 72e70d6e298f
roll-advisor is a skill published in the GitHub repository sumimakito/roll (2 stars, last pushed 4mo ago), licensed MIT. It adds 32 tokens to every session and 350 once invoked, about $0.0001 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…