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 agentmods add commands/abstractonion/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/commands/abstractonion/cadence/own-pr)<a href="https://agentmods.dev/commands/abstractonion/cadence/own-pr"><img src="https://agentmods.dev/badge/commands/abstractonion/cadence/own-pr.svg" alt="Measured on agentmods" 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 | $0.00029 | $0.00569 |
| Opus 5 | $0.00015 | $0.00284 |
| Sonnet 5 | $0.00006 | $0.00114 |
| Haiku 4.5 | $0.00003 | $0.00057 |
Grade A, and why
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 6d 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.
- 6d ago First seen · 36 lines · 29 tokens per session scan A 4511dbf0603a
own-pr is a command published in the GitHub repository abstractonion/cadence (4 stars, last pushed 2mo ago), licensed MIT. It adds 29 tokens to every session and 569 once invoked, about $0.0001 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 commands, from other repositories
devkit.github.review-pr
Provides comprehensive GitHub pull request review with code quality, security, and best practices analysis. Use when reviewing a PR before merging.
speckit.spex.submit
Push and create PR for team review, with optional watch mode for CI monitoring.
git
The pre-finish status: branch, hygiene findings, message checks, workflow lint, template state.
code-review
Code review for branch changes. Analyzes git diff between branches with multi-level depth (low/medium/high). Matches changes against task description. Returns structured report with severity levels and verdict.
repo-audit
Audit a codebase (local or remote GitHub/GitLab) against architecture principles and requirements, surfacing drift, risk, and missing decisions.
advanced-code-review-context
Advanced Code Review Phase 2: Context Analysis - load previous reviews, PR history, declined items.