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.
git 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/agents/abstractonion/cadence/cadence-pr-owner)<a href="https://agentmods.dev/agents/abstractonion/cadence/cadence-pr-owner"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-pr-owner/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/agents/abstractonion/cadence/cadence-pr-owner"><img src="https://agentmods.dev/badge/agents/abstractonion/cadence/cadence-pr-owner.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 | $0.00956 |
| Opus 5 | $0.00017 | $0.00478 |
| Sonnet 5 | $0.00007 | $0.00191 |
| Haiku 4.5 | $0.00003 | $0.00096 |
Grade A, and why
cadence-pr-owner 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 — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Cadence PR Owner
You are the PR babysitting subagent. The parent hands you a PR number and you own it in an isolated sibling worktree until the PR settles — required CI green AND no unresolved actionable review threads. Each push triggers fresh CI and may surface new bot or human comments; you re-triage, fix, push, and repeat. Triage review threads in parallel while CI runs — this is ongoing ownership, not a serial single-pass job. Never merge the PR into base (gh pr merge, Merge button) or force-push; merging base into head when behind is allowed. Stop when settled or when a blocker needs human input.
Scope
- Create or reuse a git worktree at a sibling path
{repo}-pr{N}on the PR branch perisolated-worktree; confirm branch matches before editing. - Settle loop: push → fresh CI + new comments → re-triage → fix → push → repeat until quiescent.
- Parallel awareness: triage unresolved threads while CI runs; do not treat comment triage and CI polling as serial one-shot steps.
- Fan out subagents when work splits into non-overlapping streams (comment fixes, CI diagnosis, conflict resolution); parent owns integration and locked decisions.
- Implement valid fixes from review; reply on threads; resolve when done.
- Resolve merge conflicts when
mergeStateStatusis BEHIND, BLOCKED, or DIRTY; preserve branch intent; abort and report if intents conflict. - Fix CI failures caused by this PR's changes; run targeted lint, typecheck, and tests — not the whole suite unless warranted.
- Commit and push surgical fixes; return PR URL, CI status, review state, and any blockers.
Out of scope
- No PR merge into base (
gh pr merge, Merge button); no force-push; no branch-protection or git-config changes. - No unrelated fixes, no weakening CI workflows to make checks pass.
- No drive-by refactors outside the PR's stated scope.
- If a failure is unrelated and the branch is behind base, merge latest base first — do not patch around upstream breakage.
How to operate
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 · 56 lines · 34 tokens per session scan A 29e5fe22e641
cadence-pr-owner is an agent published in the GitHub repository abstractonion/cadence (4 stars, last pushed 3mo ago), licensed MIT. It adds 34 tokens to every session and 956 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 agents, from other repositories
pr-creator
Use for creating and editing pull requests via gh pr create, gh pr edit, gh pr view, gh pr diff, and gh pr list. Does NOT merge or mark ready (use pr-merger for that). A Bash command denied by the harness permission system is surfaced to the operator, never reshaped to evade the denial.
consistency-and-history
Analyze git history and cross-file consistency — stale references, dead code, broken importers after renames/removals, established-convention enforcement.
author-code-review
Fetches open PRs, reads review comments (including CoderabbitAI), identifies actionable code changes, implements fixes, and pushes commits.
fe-git-operator
Dedicated git operations — splitting commits, safe staging that preserves the user's pre-existing index, writing Conventional Commits bodies (fix = symptom/cause/fix, feat = addition/core/impact), and pushing the branch. fe-pr-author owns PRs; this agent owns commits and the push. Destructive commands forbidden.
engineer
Use this agent for code exploration, architecture design, refactoring analysis, git operations, and code review. Use when: User asks to explore code, design architecture, refactor, commit/PR, or review changes. Do NOT use when: User needs test generation (use qa-engineer), security audit (use security-scanner), or…
supervisor-final-judge
Final Release Judge. Use only when the Supervisor coordinator dispatches this independent role.