A workflow for checking GitHub pull requests, diagnosing GitHub Actions failures, handling draft status, using the merge queue, and confirming that a change was actually merged. A pull request is a proposed code change reviewed before it enters the main branch; CI is automated checking of that change.

Use it to review pull-request state, read failed CI logs, mark work ready, enqueue approved changes, and verify the final merged state.

It prevents merging work that is still marked as unfinished, has failing checks, or was only placed in a queue without actually landing. It also gives a consistent way to inspect failures and status.

How tsz-org/tsz configures Claude Code and Codex

Reuse

Borrowing it

Nothing to install: this file belongs to tsz-org/tsz. 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/tsz-org/tsz/main/.agents/skills/tsz-ci-pr/SKILL.md

Clone the repo

git clone --depth 1 https://github.com/tsz-org/tsz

Made for: Claude Code, Codex.

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/tsz-org/tsz/tsz-ci-pr/github.svg)](https://agentmods.dev/skills/tsz-org/tsz/tsz-ci-pr)

Your own site

<a href="https://agentmods.dev/skills/tsz-org/tsz/tsz-ci-pr"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-ci-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/tsz-org/tsz/tsz-ci-pr"><img src="https://agentmods.dev/badge/skills/tsz-org/tsz/tsz-ci-pr.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 66 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 660 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	$0.00066	$0.00660
Opus 5.5	$0.00026	$0.00264
Sonnet 5.5	$0.00013	$0.00132
Haiku 4.5	$0.00007	$0.00066

Measured 23d ago against content hash 050d0ad4364e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tsz-ci-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 23d 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.

.agents/skills/tsz-ci-pr/SKILL.md · 61 lines

How it starts

The opening of the file, as written. The whole thing — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.

TSZ CI And PR

Use for PR checks, CI triage, ready state, queue evidence, and landing. Use tsz-pr-coordination for PR body/label contract.

Rules

Use gh; sign substantive comments with a provenance line (e.g. Machine: studio or Provenance: studio / claude-code / claude-opus-4-8 / high).
The PR author lands their own PR; never idle-wait on CI between pushes.
Never merge draft/WIP PRs (draft, WIP, [WIP], or body/branch says WIP).
Every open PR runs the full CI suite (draft or not); path-based content skips apply only to docs-only or tooling-only diffs.
Ready PRs land through GitHub's native merge queue.
If asked to land, verify state: MERGED; an armed queue request alone is not enough.

Inspect

gh pr view <pr> --json state,isDraft,mergeStateStatus,mergeable,autoMergeRequest,mergedAt,labels,title,url,headRefName,headRefOid
gh pr checks <pr> --json name,state,bucket,link,completedAt
gh run view <run-id> --log-failed
gh run view <run-id> --job <job-id> --log

Use gh pr checks <pr> --watch --interval 20 only when the result is needed now.

Landing

Confirm not WIP and head SHA matches inspected checks.
Fix failures in-PR; comment with root cause and verification.
Mark ready only after implementation and verification: gh pr ready <pr>.
Queue with GitHub's native merge queue only when exact-head PR-head checks such as CI Summary pass and policy permits: gh pr merge <pr> --match-head-commit <sha>. Do not pass --auto; with branch protection and passing checks, current gh adds the PR to the native merge queue directly.
Inspect merge_group CI runs if queue validation stalls.
Verify final merge: gh pr view <pr> --json state,mergedAt,mergedBy,url.

Failure Hints

CI Summary: umbrella PR-head status.
merge_group CI: native queued-merge summary validation.
conformance-aggregate: accepted-regression drift can fail aggregate even when shards pass.
unit-cloudbuild: often exposes memory, linking, or architecture guard failures.
Docs-only and bench-shell-only paths short-circuit most jobs.

Read the full file on GitHub · 61 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.

23d ago First seen · 61 lines · 66 tokens per session scan A 050d0ad4364e

Subscribe to this mod's changes

tsz-ci-pr is a skill published in the GitHub repository tsz-org/tsz (577 stars, last pushed today), licensed Apache-2.0. It adds 66 tokens to every session and 660 once invoked, about $0.0003 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 2026-09-28.

CI and CD DevOps and cloud Git and workflow Rust

deployment-rules

Release/deployment standards — semantic-release, commitlint, version sync, the updater. Load for /prepare-release and changes to release.config.mjs / commitlint / workflows / version files. Owned by project-steward.

saeedkolivand/ai-job-hunter-app · 49 tokens

release-publish

Pre-publish and publish path for crates.io, npm installer, GitHub Releases, SBOM. Use when cutting versions, editing release.yml, or adding publish steps. Never publish from a feature branch.

KalarisLabs/Skill-Doctor · 45 tokens

publish-release

Publish a new nudge release end-to-end — version bump PR, v-tag, GitHub release with notes, and the CI pipeline that builds binaries/APK and updates Homebrew + AUR. Use when asked to release, publish, ship, or tag a new version. Encodes the exact merge-gate and notes-before-artifacts ordering, so no step needs…

nuudge/nudge · 81 tokens

deployment-patterns

Deployment workflows, CI/CD pipeline patterns, Docker containerization, health checks, rollback strategies, and production readiness checklists for web applications. Use when setting up deployment infrastructure or planning releases.

affaan-m/ECC · 41 tokens

agent-github-modes

Agent skill for github-modes - invoke with $agent-github-modes.

ruvnet/ruflo · 21 tokens

update-v8-version

Update Codex's pinned v8 / rustyv8 versions, validate the release-candidate path, and investigate failed V8 canary or artifact builds. Use when asked to bump V8, update rustyv8 artifacts, prepare or validate a V8 release candidate, check v8-canary, or diagnose why a V8 version update no longer builds.

openinterpreter/openinterpreter · 86 tokens

tsz: Skill for Claude Code