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 abstractonion/cadence --skill cadence-own-prgit clone --depth 1 https://github.com/abstractonion/cadenceWrote 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/abstractonion/cadence/cadence-own-pr)<a href="https://agentmods.dev/skills/abstractonion/cadence/cadence-own-pr"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/cadence-own-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/abstractonion/cadence/cadence-own-pr"><img src="https://agentmods.dev/badge/skills/abstractonion/cadence/cadence-own-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 | $0.00031 | $0.00570 |
| Opus 5 | $0.00015 | $0.00285 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
cadence-own-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 11d 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 — 36 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Own PR
Manual/user-invoked only — do not auto-select this workflow from description matching. Enter PR babysit mode only when the user explicitly invoked /own-pr (or /cadence:own-pr).
Babysit PR #N until settled — required CI green AND no unresolved actionable review threads. Ongoing loop, not a single pass. In Cursor/Claude Code, prefer delegating to the cadence-pr-owner subagent when available.
Pass the PR number from the user's message (or ask if missing). Work in sibling worktree {repo}-pr{N} per isolated-worktree. Do not merge the PR into base (gh pr merge, Merge button) or force-push; merging base into head when behind is allowed.
How to operate
gh pr view N --json url,headRefName,baseRefName,mergeable,mergeStateStatus,statusCheckRollup; create worktree at{repo}-pr{N}if missing; confirm branch matches.- Fetch unresolved review comments; filter resolved. Read only bodies/locations needed to act.
- Partition before fixing. Fan out fresh subagents per
parallel-workstreamswhen comment triage, CI diagnosis, and conflict resolution are disjoint; serialize shared wiring. - Fix valid issues; run lint, typecheck, targeted tests per
run-lint-and-typecheck/verify-with-runtime; integrate subagent diffs before push. - If
mergeStateStatusis BEHIND, BLOCKED, or DIRTY: merge base into head — prefergit fetch origin && git merge origin/{baseRefName}; orgh pr update-branchthengit fetch origin && git merge origin/{headRefName}(or ff-only pull) before push. Resolve conflicts. Rebase only if user explicitly approves force-with-lease. - Stage PR-scoped files only; commit; push; reply on addressed threads.
- Settle loop — repeat: triage new threads while CI runs; poll
gh pr checks N --required; fix and push. - Stop when: required checks pass AND no unresolved actionable threads — or explicit human blocker (permissions, product decision, ambiguous scope).
Return PR URL, CI status, review state, blockers.
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.
- 11d ago First seen · 36 lines · 31 tokens per session scan A 1101121acc5b
cadence-own-pr is a skill published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 31 tokens to every session and 570 once invoked, about $0.0002 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 2026-08-31.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
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.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
End-to-end playbook for shipping high-quality pull requests to open-source projects you don't maintain — discovery, CONTRIBUTING compliance, PR-size check, minimal-diff implementation, PR description with AI-assisted disclosure, conflict resolution, and post-submission maintainer interaction. Use whenever creating…
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…
oss-maintainer
Run an open-source project's issue/PR/release loop like a careful human maintainer — triage to root cause, absorb community PRs before duplicating them, gate every merge, ship honest releases, and thank the people doing your QA for free.