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-observegit 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-observe)<a href="https://agentmods.dev/skills/sumimakito/roll/roll-observe"><img src="https://agentmods.dev/badge/skills/sumimakito/roll/roll-observe/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-observe"><img src="https://agentmods.dev/badge/skills/sumimakito/roll/roll-observe.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 | $0.00034 | $0.00538 |
| Opus 5.5 | $0.00014 | $0.00215 |
| Sonnet 5.5 | $0.00007 | $0.00108 |
| Haiku 4.5 | $0.00003 | $0.00054 |
Grade A, and why
roll-observe 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-observe
Return one verdict: green, failed, conflicted, review-blocked, or
gave-up. Merge-ready requires passing checks, clean mergeability, and required
reviews.
Default Shape
Tell the user once that checks are watched live while conflicts are polled, so the interval isn't read as the only mechanism.
Run two concurrent processes:
- Checks watcher:
gh pr checks <pr> --watch. - Conflict poller every
CONFLICT_POLL_INTERVALdefault 10 min:gh pr view <pr> --json mergeable,mergeStateStatus.
If any poll returns mergeable=CONFLICTING or mergeStateStatus=DIRTY, kill
the watcher and return conflicted. If the watcher exits first, reconcile.
Fallbacks
Use the best supported shape:
- Host scheduler tick: each tick reads checks plus mergeability JSON.
- Two-process watch plus poller: default.
- Foreground poll loop: read checks and mergeability each interval. Do not use
a bare blocking
--watch; it misses early conflicts.
Reconcile
After any watch exit, read current truth:
gh pr checks <pr>
gh pr view <pr> --json mergeable,mergeStateStatus,reviewDecision,statusCheckRollup
- Terminal checks: decide verdict from current truth.
- Pending/in_progress checks: watch likely died early; re-watch with backoff,
capped by
MAX_REWATCHdefault 5. gh pr checksexits 8: treat as no checks to wait for.
Caps
- Honor remaining shared
MAX_WALLfromroll; do not start a new timer. - On
MAX_REWATCHor wall-clock cap hit, returngave-up. - Avoid polling so fast that
gh/API rate limits become likely.
Verdict Rules
green: checks pass, mergeability clean, required reviews met.failed: required check failed.conflicted:mergeable=CONFLICTINGormergeStateStatus=DIRTY.review-blocked: reviews or required reviewers block merge.gave-up: cap hit or no stable verdict.
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 · 55 lines · 34 tokens per session scan A 69c19aff2b22
roll-observe is a skill published in the GitHub repository sumimakito/roll (2 stars, last pushed 4mo ago), licensed MIT. It adds 34 tokens to every session and 538 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
deployment-patterns
Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.
agent-github-modes
Agent skill for github-modes - invoke with $agent-github-modes.
baby-sit
Monitor a GitHub pull request until CI is green, diagnose failures, and rerun only evidence-backed flaky GitHub Actions jobs.
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-hooks
Atmos hooks: lifecycle events, hook kinds, command/store/git/security hooks, step/steps hooks, when: conditions, scoping and overrides, toolchain integration, --skip-hooks, and Atmos Pro/local output.
atmos-pro
Atmos Pro setup and workflows: settings.pro, GitHub OIDC, affected and inventory uploads, stack locks, pro commit, workflow dispatch, merge queues, and drift detection.