A pull-request status helper that waits for GitHub Actions checks and review-bot feedback after a pull request is opened or updated, then combines the results into one report.

Use it after creating a pull request or pushing a new commit to its branch. It reports completed, failed, skipped, cancelled, or still-blocked checks and review feedback together.

It removes the need to repeatedly check whether automated tests, builds, and review comments have finished. It also flags checks that need manual approval.

How dburkart/auto-engineer configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to dburkart/auto-engineer. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/dburkart/auto-engineer/main/.claude/skills/wait-for-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/dburkart/auto-engineer

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/dburkart/auto-engineer/wait-for-pr/github.svg)](https://agentmods.dev/skills/dburkart/auto-engineer/wait-for-pr)

Your own site

<a href="https://agentmods.dev/skills/dburkart/auto-engineer/wait-for-pr"><img src="https://agentmods.dev/badge/skills/dburkart/auto-engineer/wait-for-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/dburkart/auto-engineer/wait-for-pr"><img src="https://agentmods.dev/badge/skills/dburkart/auto-engineer/wait-for-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 53 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 1,237 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00053	$0.01237
Opus 5.5	$0.00021	$0.00495
Sonnet 5.5	$0.00011	$0.00247
Haiku 4.5	$0.00005	$0.00124

Measured 1mo ago against content hash c83dfced2ed2, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

wait-for-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 1mo 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.

.claude/skills/wait-for-pr/SKILL.md · 127 lines

How it starts

The opening of the file, as written. The whole thing — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.

wait-for-pr

Read docs/agent-playbooks/pr-review.md first for repo-level CI readiness and review-classification rules.

This skill keeps only the Claude-specific wait loop and automation needed to turn shared review rules into a single consolidated PR-status report.

When to invoke

Immediately after gh pr create / mcp__github__create_pull_request returns a PR URL.
After pushing a follow-up commit to a PR branch (re-enter the loop to confirm green).
When the user says "wait for CI," "check the PR," or similar.

Identifying the PR

If the PR number isn't already known from the preceding tool call:

gh pr list --head "$(git branch --show-current)" --json number,url --jq '.[0]'

Record the number and URL; reuse them for every poll tick.

What "done" means

The PR isn't ready for a summary until all are true:

Every GitHub Actions check is in a terminal state: success, failure, skipped, cancelled, neutral, timed_out, or stale. Nothing in_progress, queued, or pending.
No check is sitting in action_required waiting on manual approval (flag it and stop — the user needs to act).
At least one review-bot comment / review exists, or 30 minutes have elapsed since the PR opened (bots may not be wired up; don't block forever).

Poll cadence

Use ScheduleWakeup between ticks. Tune delaySeconds to stay friendly to the 5-minute prompt-cache TTL:

Elapsed since PR opened	delaySeconds
0–10 min	120
10–30 min	180 (still under the 270 s cache window)
30 min+ (waiting only on slow bots)	1200

Never pick 300 s — it's the worst of both worlds (cache miss with no payoff). Under 10 minutes, stay ≤ 270 s.

Each poll tick

Check CI state:
```
gh pr checks <PR> --json name,state,bucket,link
```
or mcp__github__get_pull_request_status.

Count review-bot activity:

gh api "repos/dburkart/auto-engineer/issues/<PR>/comments" \
  --jq '[.[] | select(.user.login | test(""))] | length'

Also fetch formal reviews via mcp__github__get_pull_request_reviews.

Read the full file on GitHub · 127 lines

Changes

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.

1mo ago First seen · 127 lines · 53 tokens per session scan A c83dfced2ed2

Subscribe to this mod's changes

wait-for-pr is a skill published in the GitHub repository dburkart/auto-engineer (5 stars, last pushed 6mo ago), licensed BSD-3-Clause. It adds 53 tokens to every session and 1,237 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 2026-08-31.

Git and workflow Testing

codew-release-qa-sweep

Use before claiming Codewhale release work is done: run the full gate sweep and list the manual QA targets.

Hmbown/CodeWhale · 31 tokens

emerging-techniques-model-merging

Merge multiple fine-tuned models using mergekit to combine capabilities without retraining. Use when creating specialized models by blending domain-specific expertise (math + coding + chat), improving performance beyond single models, or experimenting rapidly with model variants. Covers SLERP, TIES-Merging, DARE, Task…

davila7/claude-code-templates · 77 tokens

mem0-test-integration

Verify a Mem0 integration produced by /mem0-integrate. Runs in the same workspace on the same branch (loose coupling) — installs dependencies, runs the repo's native test suite, then exercises a real end-to-end smoke flow against the user's API key. Produces a scorecard. TRIGGER when: user has just run /mem0-integrate…

mem0ai/mem0 · 207 tokens

auto-engineer: Skill for Claude Code