parallel-debug

A debugging workflow that repeatedly checks all open pull requests in the claude-dev-env project until its bug review and bug-team review agree at the same code version.

In plain words
What is it for?
Use it to run the project’s pull-request convergence loop in Cursor, continuing until reviews are clean or a blocker is reached.
Why use it?
It helps drive open pull requests toward a shared clean result instead of handling each review only once.

Skill for Claude CodeCodexCursor

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.

agentmods
npx agentmods add skills/jl-cmd/claude-dev-env/parallel-debug
Any agent
npx skills add jl-cmd/claude-dev-env --skill parallel-debug
Clone the repo
git clone --depth 1 https://github.com/jl-cmd/claude-dev-env

Made for: Claude Code, Codex, Cursor.

Per session 50 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,127 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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.

ModelPer sessionOnce invoked
Fable 5 $0.00050 $0.03127
Opus 5 $0.00025 $0.01563
Sonnet 5 $0.00010 $0.00625
Haiku 4.5 $0.00005 $0.00313

Measured 2d ago against content hash 7dae003c7e27, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

parallel-debug 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.

.cursor/skills/parallel-debug/SKILL.md · 231 lines

How it starts

The opening of the file, as written. The whole thing — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Run the bugbot + bugteam convergence loop across all open PRs in jl-cmd/claude-dev-env, paced by an AHK auto-typer instead of ScheduleWakeup (which is unavailable in Cursor sessions). End every response with Awaiting next "continue" tick.

Objective

Converge every open PR in jl-cmd/claude-dev-env to back-to-back clean: bugbot CLEAN + bugteam CLEAN at the same HEAD. Mark each converged PR ready for review with gh pr ready. Stop when all open PRs have converged or hit a hard blocker.

One-Time Setup

Run these two commands at the start of the session before any tick work:

1. Resolve the Cursor window PID:

pwsh -NoProfile -ExecutionPolicy Bypass -File "$HOME\.claude\skills\pr-converge\scripts\caller-window-pid.ps1"

Capture the printed integer as caller_pid. Verify it is the right window:

pwsh -NoProfile -Command "Get-Process -Id <caller_pid> | Select-Object Id,ProcessName,MainWindowTitle"

2. Launch the AHK auto-typer:

"$HOME\.claude\skills\pr-converge\scripts\cursor-agents-continue.cmd" <caller_pid> --start-on

AutoHotkey v2 must be installed at C:\Program Files\AutoHotkey\v2\AutoHotkey64.exe. The indicator window (pr-converge / agents pacer) confirms the pacer is running. Every 5 minutes it types continue into this window to trigger the next tick.

Step 0: Discover Work Queue

At the start of each session (or after a long pause), assemble the current PR state dynamically. Run all four commands:

Open PRs:

gh api 'repos/jl-cmd/claude-dev-env/pulls?state=open&per_page=100' --paginate --slurp \
  | jq '[.[][] | {number, title, headRefName: .head.ref, head_sha: .head.sha, mergeable, isDraft: .draft}] | sort_by(.number)'

Use head.ref and draft here — the REST list response does not expose GraphQL-style headRefName / isDraft keys. gh pr view --json (below) is what emits headRefName / isDraft.

Bugbot review status per PR (run for each <N>):

python "$HOME\.claude\skills\pr-converge\scripts\fetch_bugbot_reviews.py" \
  --owner jl-cmd --repo claude-dev-env --number <N>

Returns classification: "clean" or classification: "dirty" plus commit_id.

Read the full file on GitHub · 231 lines

Files

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.

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.

  1. 2d ago First seen · 231 lines · 50 tokens per session scan A 7dae003c7e27

Subscribe to this mod's changes

parallel-debug is a skill published in the GitHub repository jl-cmd/claude-dev-env (6 stars, last pushed 2d ago), licensed MIT. It adds 50 tokens to every session and 3,127 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens