What is handle-failing-pr-ci?

An automated workflow for finding your open GitHub pull requests with failing continuous integration checks and starting a separate fix session for each one. Continuous integration, or CI, automatically builds and tests code when changes are submitted.

Use it to list failing pull requests, prepare isolated workspaces, and dispatch agents to fix their CI failures.

It removes the manual work of checking every pull request and setting up each fix. Independent failing pull requests can be handled at the same time in separate Git worktrees.

handle-failing-pr-ci — Skill for Claude Code by tomzx/agents

Install

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.

Any agent

npx skills add tomzx/agents --skill handle-failing-pr-ci

Clone the repo

git clone --depth 1 https://github.com/tomzx/agents

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/tomzx/agents/handle-failing-pr-ci/github.svg)](https://agentmods.dev/skills/tomzx/agents/handle-failing-pr-ci)

Your own site

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

Per session 92 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,869 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	$0.00092	$0.02869
Opus 5.5	$0.00037	$0.01148
Sonnet 5.5	$0.00018	$0.00574
Haiku 4.5	$0.00009	$0.00287

Measured 22d ago against content hash 318461cf72c3, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

handle-failing-pr-ci 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 22d 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.

skills/handle-failing-pr-ci/SKILL.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Handle Failing PR CI

Lists the current user's open pull requests with their combined CI status, then fixes every PR whose checks are failing by giving each one its own handle-pr-ci session. PRs are independent, so they are processed in parallel: one sub-agent per failing PR, each with its own worktree.

The orchestrator (this session) only discovers work and prepares worktrees. It never edits code. Each failing PR is handled end to end by one sub-agent running handle-pr-ci.

Prerequisites

Apply the shared SDLC conventions in skills/sdlc/references/shared.md.
uv installed (for running the Python script)
gh CLI authenticated with read/write access to the target repositories
git with git worktree available
The handle-pr-ci skill available
Sub-agent dispatch via the Task tool (subagent_type: "general"). If unavailable, use sequential mode instead.

Workflow

Run ~/.agents/scripts/my_prs_ci.py --json
              |
              v
  Keep PRs with checks_state == "failing"
              |
              v
  Group by repo, prepare one worktree per failing PR
              |
              v
  Fan out: one general subagent per PR, concurrently
              |
              |   subagent A -> /handle-pr-ci <PR A>   subagent B -> <PR B>   ...
              |      (owns its worktree; diagnoses, fixes, pushes, watches CI)
              |
              v
  Collect VERDICT lines -> summary table

Steps

1. Discover my PRs and their CI status

Run the discovery script:

~/.agents/scripts/my_prs_ci.py $@ --exclude-check "PR Review Bot Comments Addressed" --json

The PR Review Bot Comments Addressed check is excluded by default because it is a noisy bot gate that does not reflect actual CI health. Any --exclude-check / --include-check the user passes is applied on top of it, and exclusions take precedence, so the bot check stays excluded. To include it in a particular run, scope the query with an explicit PR URL and call the script directly without this skill.

Read the full file on GitHub · 258 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.

22d ago Changed · +27 lines 318461cf72c3
25d ago Changed 2ca2f6d4a00a
1mo ago First seen · 231 lines · 92 tokens per session scan A a2ed67b3c3bc

Subscribe to this mod's changes

handle-failing-pr-ci is a skill published in the GitHub repository tomzx/agents (13 stars, last pushed yesterday), licensed MIT. It adds 92 tokens to every session and 2,869 once invoked, about $0.0004 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 2026-09-19.

CI and CD DevOps and cloud Git and workflow

handle-failing-pr-ci

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

Handle Failing PR CI

Prerequisites

Workflow

Steps

1. Discover my PRs and their CI status

What this file has done since we first saw it

Other skills, from other repositories

deployment-patterns

agent-github-modes

baby-sit

chinese-git-workflow

atmos-hooks

atmos-pro