Borrowing it
Nothing to install: this file belongs to avibe-bot/avibe. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/avibe-bot/avibe/master/.agents/skills/pr-delivery-loop/SKILL.mdgit clone --depth 1 https://github.com/avibe-bot/avibeWrote 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/avibe-bot/avibe/pr-delivery-loop)<a href="https://agentmods.dev/skills/avibe-bot/avibe/pr-delivery-loop"><img src="https://agentmods.dev/badge/skills/avibe-bot/avibe/pr-delivery-loop/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/avibe-bot/avibe/pr-delivery-loop"><img src="https://agentmods.dev/badge/skills/avibe-bot/avibe/pr-delivery-loop.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Agent Snooping · line 11 Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
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 | $0.00055 | $0.02875 |
| Opus 5.5 | $0.00022 | $0.01150 |
| Sonnet 5.5 | $0.00011 | $0.00575 |
| Haiku 4.5 | $0.00006 | $0.00287 |
Grade A, and why
pr-delivery-loop 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 2d 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 — 113 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PR Delivery
Your job is to deliver a change for real: pass review and CI, then Merge it, or drive it to Merge-ready so that only the user's approval remains. There is no intermediate "state" where you can stop. Whenever you are resumed, inspect the live situation first and answer two questions: what is still between this PR and Merge, and what is the most useful thing I can do now? Then do it.
The reasons behind these rules, with the failures that produced them, are in references/rationale.md. Read the relevant section when a rule seems wrong for your situation or a failure is unfamiliar; routine delivery does not need it.
Keep moving
- Fix problems. Investigate findings, CI failures, and conflicts to their root cause; make the smallest complete fix, verify it, and push.
- Wait for a named signal. Waiting is real only when you can say which signal you need, who produces it, and how you will know it arrived. Let the Watch monitor it. Use the time to add tests, check consumers, and prepare the close-out report; continue as soon as the signal arrives. If you cannot say what you are waiting for, you are not waiting—you are stopped.
- A blocker is a problem to solve, not a reason to stop. Diagnose it yourself, break it down, try another path, and gather evidence. Stop only when a major trade-off, an authorization outside your scope, or an irreversible risk requires the user's decision; state exactly what decision is needed.
- Trust live state only. Each round, fetch the current head, all reviews, comments, and threads (including outdated ones), and CI for the current head. Old snapshots, previous green results, and lane conclusions are clues only.
- Dig deeper when a pattern repeats. If the same root cause appears on two reviewed heads, or three consecutive heads still have findings after an architectural rewrite, you are treating symptoms. Stop patching, build a complete inventory, find the real cause, define the smallest complete scope, and continue. This changes the method; it does not stop the work.
What ships with it
2 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 2d ago Changed · +1 lines 11d50ac06fd1
- 8d ago Changed · -122 lines · +11 tokens per session 8a365d9352d6
- 10d ago Changed · -35 lines · -14 tokens per session 635056573024
- 1mo ago Changed · +4 lines 74824f8511cb
- 1mo ago Changed · +5 lines 850b37b42101
- 1mo ago Changed · -148 lines · -20 tokens per session e32db27d267d
- 1mo ago First seen · 408 lines · 78 tokens per session scan A 6ea65528209a
pr-delivery-loop is a skill published in the GitHub repository avibe-bot/avibe (633 stars, last pushed today), licensed MIT. It adds 55 tokens to every session and 2,875 once invoked, about $0.0002 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 2026-08-30.
Other skills, from other repositories
meta-issue-to-pr-autopilot
Triages an issue, delegates the fix to sub-agent, drafts a PR description with summarize, and opens the PR via gh. Best used on small, well-scoped issues with clear acceptance criteria.
meta-github-pr-watch-digest
Inspect the user's open GitHub PRs / failing CI / new issues via gh, summarize into 3 buckets (to-review / awaiting-me / CI-red), and persist follow-ups to memory.
project-setup
Add a GitHub repository as a tracked project — creates workspace entity, installs workflow automation missions, and includes in dev brief scope.
github-workflow
Install and operate a full GitHub issue-to-merge workflow for any repository using event-driven and cron missions. Handles issue planning, PR monitoring, CI fixing, staging review, and post-merge learning.
github-issues
Create, search, triage, label, assign, comment on, and close GitHub issues using the gh CLI, with a curl REST fallback.
gh-issues
Fetch GitHub issues, spawn sub-agents to implement fixes and open PRs, then monitor and address PR review comments. Usage: /gh-issues [owner/repo] [--label bug] [--limit 5] [--milestone v1.0] [--assignee @me] [--fork user/repo] [--watch] [--interval 5] [--reviews-only] [--cron] [--dry-run] [--model glm-5]…