A pull-request convergence loop that combines code review, bug audits, Cursor Bugbot, and GitHub Copilot, applying test-driven fixes until all available checks are clean on the same revision.

Use it to drive a draft pull request toward a clean, mergeable state while checking bugs, code quality, and automated reviewer findings.

It coordinates several review systems and repeats the fix-and-review cycle, reducing the need to track their results manually.

pr-converge — Skill for Claude Code by jl-cmd: A pull-request convergence loop that combines code review, bug…

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/pr-converge

Any agent

npx skills add jl-cmd/claude-dev-env --skill pr-converge

Clone the repo

git clone --depth 1 https://github.com/jl-cmd/claude-dev-env

Made for: Claude Code.

Or install claude-dev-env, the plugin that ships this one along with the rest of its 64 skills, 3 commands, 9 agents, 8 hooks.

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/jl-cmd/claude-dev-env/pr-converge.svg)](https://agentmods.dev/skills/jl-cmd/claude-dev-env/pr-converge)

Your own site

<a href="https://agentmods.dev/skills/jl-cmd/claude-dev-env/pr-converge"><img src="https://agentmods.dev/badge/skills/jl-cmd/claude-dev-env/pr-converge.svg" alt="Measured on agentmods" height="20"></a>

Per session 87 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 6,710 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.

Model	Per session	Once invoked
Fable 5.1	$0.00087	$0.06710
Opus 5	$0.00044	$0.03355
Sonnet 5	$0.00017	$0.01342
Haiku 4.5	$0.00009	$0.00671

Measured 6d ago against content hash 98a656efcf77, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

pr-converge 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 6d ago.

The scan reads SKILL.md. This mod also ships 27 executable files (pr_converge_skill_constants/__init__.py, pr_converge_skill_constants/constants.py, scripts/_pr_converge_path_setup.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

packages/claude-dev-env/.agents/skills-archived/pr-converge/SKILL.md · 470 lines

How it starts

The opening of the file, as written. The whole thing — 470 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PR Converge

A code-review ↔ bugteam ↔ Bugbot ↔ Copilot loop on a draft PR: the internal code-review and bugteam passes drive the code to clean first, then Cursor Bugbot and Copilot run as terminal confirmation gates, until all are clean on the same HEAD and mergeable. On pacer=schedule_wakeup, one tick runs per invocation and the next tick is scheduled. On pacer=portable, ticks run continuously in-session (see ../../skills/_shared/pr-loop/portable-driver.md).

Transport check (before any GitHub step)

Run command -v gh; when it succeeds, run gh auth status; once the PR scope is resolved, run gh api repos/<owner>/<repo> --jq .permissions.push and take true as the pass. When any check fails, run the pr-loop-cloud-transport skill first and route every gh operation in this skill through its substitution matrix.

Pre-flight

Task list (step 1)

After down/opt-out flags are known, build the work list with build_converge_task_list.py only (same script as autoconverge). Register every task; final task is always all_runnable_reviews_clean_same_head. Complete that final task only when every runnable review is CLEAN on the same HEAD. On pacer=portable, open-run returns the same list.

Pacer selection

Scan the tool list for ScheduleWakeup. Record whether it is present, then select the pacer:

python "$HOME/.claude/skills/_shared/pr-loop/scripts/select_converge_pacer.py" \
  --skill pr-converge \
  --has-workflow <0|1> \
  --has-schedule-wakeup <0|1>

pacer=schedule_wakeup — native tick pacing via ScheduleWakeup (see workflows/schedule-wakeup-loop.md).
pacer=portable — continuous in-session driver on ../../skills/_shared/pr-loop/portable-driver.md. Do not abort because ScheduleWakeup is missing.

Worktree isolation

When the tool list includes EnterWorktree, call it with no arguments before any API call, file read, or edit. Agent-view sessions start in the shared checkout; Bash (gh, git) does not auto-isolate. Do not proceed until the working directory contains .claude/worktrees/. If EnterWorktree fails, report the failure and stop.

Read the full file on GitHub · 470 lines

Files

What ships with it

60 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.

6d ago First seen · 470 lines · 87 tokens per session scan A 98a656efcf77

Subscribe to this mod's changes

pr-converge is a skill published in the GitHub repository jl-cmd/claude-dev-env (5 stars, last pushed today), licensed MIT. It adds 87 tokens to every session and 6,710 once invoked, about $0.0004 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.

Code review TDD Testing

engram-testing-coverage

TDD and coverage standards for Engram. Trigger: When implementing behavior changes in any package.

Gentleman-Programming/engram · 25 tokens

nunit-testing

Use when writing or modifying tests in NUnit's own test projects, or when making a behavioral change to production code that needs test coverage. Covers test structure, attribute choice, helper visibility, platform guards, and which test projects are real.

nunit/nunit · 51 tokens

tdd

Test-driven development. Use when the user wants to build features or fix bugs test-first, mentions "red-green-refactor", or wants integration tests.

GreyDGL/PentestGPT · 33 tokens

strict-tdd

Strict RED->GREEN->REFACTOR test-driven development with enforcement. Never write production code before a failing test. Atomic commits per TDD cycle.

a5c-ai/babysitter · 34 tokens

tdd

This skill should be used when the user wants to implement features or fix bugs using test-driven development. Enforces the RED-GREEN-REFACTOR cycle with vertical slicing, context isolation between test writing and implementation, human checkpoints, and auto-test feedback loops. Uses multi-agent orchestration with the…

glebis/claude-skills · 92 tokens

conductor-implement

Execute tasks from a track's implementation plan following TDD workflow.

rmyndharis/antigravity-skills · 17 tokens