Skip to main content
skill CX Codex

swarm-pr-feedback · zaxbyhub, claude — Claude Code skill: what it does, how to install

swarm-pr-feedback — a skill that works through PR feedback you already have: review notes, GitHub threads, failing checks, conflicts. Everything is verified against the code before a single edit lands.

MIT ★ 539 updated 2026-10-29

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add ZaxbyHub/opencode-swarm --skill swarm-pr-feedback -a claude-code
Open on GitHub

What swarm-pr-feedback does

The skill starts from feedback that already exists on a pull request: review text you paste in, GitHub comments and threads, change requests, failing checks, merge conflicts, a branch that has gone stale. All of it lands in one ledger. Each entry stays a claim until the repo proves it right or wrong, and no edit happens before that settles.

The gates run in order. Stage A covers git diff --check, a reproduction of the failing test when one is available, plus whatever build, typecheck and lint commands the repo actually has. Stage B brings in a fresh reviewer subagent, then a fresh test-engineer subagent, both on a diff that already passed Stage A. Closeout adds one more reviewer and a critic. A plain Claude session has none of the plugin's controller tools, and that is the normal Profile B path: the ledger, the ownership split and the digest accounting stay in session workspace files rather than under .swarm/. CI failures arrive as one batch via gh pr checks <n> --json name,bucket,state,link, with failed logs pulled by gh run view <run-id> --log-failed.

The PR branch is checked out locally and its HEAD compared against the authoritative SHA before anything changes; force pushes and submodule-recursive checkouts are not used. GitHub review threads stay open unless you ask for them to be resolved.

What it helps with

  • turn pasted review notes into a list of checkable items
  • pull every failing CI check in one batch instead of looping through pushes
  • compare local HEAD against the PR head before touching code
  • clear merge conflicts and a stale branch ahead of merging
  • get an independent review and test pass on a green diff

Example prompts for the agent

  • Work through the review on PR #412 and verify each point before fixing anything
  • Grab all failing checks on PR #87 in one batch and show me what broke
  • Take the branch to the finish: conflicts, review, tests, then one push without force

How to install swarm-pr-feedback

1Skills CLI (Vercel)

npx skills add ZaxbyHub/opencode-swarm --skill swarm-pr-feedback -a claude-code

2Manually: put the files in place

~/.claude/skills/swarm-pr-feedback/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/swarm-pr-feedback/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about swarm-pr-feedback

How do I install swarm-pr-feedback in Claude Code?

Run npx skills add ZaxbyHub/opencode-swarm --skill swarm-pr-feedback -a claude-code. The skill file lands at ~/.claude/skills/swarm-pr-feedback/SKILL.md.

What does swarm-pr-feedback do?

It builds a ledger of the feedback on a PR — reviews, comments, failing checks, conflicts — and checks each item against the code before changing anything. Edits wait until verification settles.

What happens when the plugin's tools aren't present in a Claude session?

That is the standard Profile B path, not a failure. Verification lanes and gate roles run as fresh Agent/Task subagents, while the skill keeps the ledger and artifact accounting in session workspace files.

Source text

SKILL.md · MIT
---
name: swarm-pr-feedback
description: >
  Claude Code adapter for closing known PR feedback. Use when addressing pasted
  review feedback, GitHub review comments or threads, requested changes,
  CI/check failures, merge conflicts, stale PR branches, or PR follow-up work
  that must verify every claim before fixing it.
metadata:
  audience: swarm-plugin
---

# Swarm PR Feedback

Read and follow `../../../.opencode/skills/swarm-pr-feedback/SKILL.md` as the canonical workflow.

## Claude Code Execution Notes

- A plain Claude Code session has none of the plugin's mechanical controller tools: that is canonical Profile B, not an error. Never report BLOCKED merely because controller tools are absent — run verification lanes and gate roles as fresh `Agent`/`Task` subagents and keep the ledger, ownership partition, and digest accounting yourself in session task workspace files (never under `.swarm/`, which is plugin runtime state).
- **Batch-collect all CI failures before proposing any fix** (Issue #1746). On GitHub, run `gh pr checks <n> --json name,bucket,state,link`, filter to `bucket == "fail" || bucket == "cancel"`, then fetch each failed log with `gh run view <run-id> --log-failed`. On other hosts, use the host-equivalent API. Build the complete failure ledger in one batch before triaging or proposing fixes — do not iterate check-by-check through push cycles.
- Check out the PR branch locally before dispatching feedback lanes or verifying/fixing anything. Fetch the head ref if absent, preserve or surface all dirty tracked/untracked state, prove full HEAD equals the authoritative PR head SHA, and prove the final branch tracks the intended PR head remote/branch. In Profile A, a detached exact-head intake is valid because the first bind attaches only one unambiguous exact tracking ref; Profiles B/C must establish the branch themselves. Never use force or submodule-recursive checkout.
- Build the complete feedback ledger before editing: pasted feedback, GitHub comments/threads, requested changes, CI/check failures, merge conflicts, stale branch state, PR body claims, linked issues, commits, and any validated `swarm-pr-review` handoff artifact. Treat every item as a claim until source evidence proves or disproves it, and preserve original finding IDs and reviewer/critic provenance from handoff artifacts.
- Verification lanes (Profile B): partition the immutable FB inventory across fresh read-only subagents — every item owned by exactly one lane, one `[FEEDBACK-VERIFIED]` row per owned item, the exact PR head SHA in every prompt — and read each subagent's full report. Under Profile A, when a lane result carries an `output_ref`, treat inline `output` as a preview and call `retrieve_lane_output` for the full artifact. Degraded, truncated, or incomplete reports keep their items open as coverage gaps: retry bounded, or surface the affected items as BLOCKED. No edits before verification settles.
- Do not resolve GitHub review threads unless the user explicitly instructs it.
- **Mandatory gates — Stage A and Stage B (+ closeout) on every profile.** Stage A always runs exact `git diff --check` plus one proof command — the exact failing CI/test reproduction when available, otherwise a repo-appropriate targeted regression/test command — plus every build, typecheck, and lint/format category mechanically discovered from the repository; it never invents a no-op category to reach a fixed count. On Profile B run these commands yourself and record command+output receipts in the ledger; any content change invalidates the receipts and restarts Stage A. Stage B: one fresh independent reviewer subagent, then one fresh test-engineer-role subagent, on the Stage-A-green diff. Closeout: a separate fresh reviewer + critic pair on the Stage-B-approved diff. One verdict row per FB ID at every gate; record both closeout verdicts in the session task-gates artifact per the durable-session-state guidance.
- Only if this session actually exposes the plugin's mechanical tools, run Profile A instead: `run_pr_feedback_stage_a`, then the exact ordered `swarm-pr-feedback:stage-b-reviewer`, `:stage-b-test`, `:closeout-reviewer`, and `:closeout-critic` structured modes, `complete_pr_workflow` arming, and the bound single-ref push. While that controller is active, direct subagent calls and free-form verdict prose are not equivalent evidence, and any edit restarts the sequence at Stage A.
- Publication (Profile B): after all gates pass on the unchanged diff, create one reviewed commit on the PR branch, push exactly that commit with a single non-force push through the repository's commit/PR workflow, then verify read-only that the remote head equals the pushed commit before any PR comment/body/thread write.

Final output must include a closure ledger for every original feedback item,
including conflicts, stale branch state, obsolete CI, and generated-output drift
when they affected the PR.

© ZaxbyHub · MIT · ZaxbyHub/opencode-swarm

Similar skills

All skills for Agent setup: memory, context, orchestration →

swarm-pr-feedback by other authors comes first.

swarm-pr-feedback ZaxbyHub swarm-pr-feedback — a skill that resolves pull request review comments, CI failures, and branch conflicts through structured verification stages. CX Codex +1 ★ 539repo stars swarm-pr-feedback ZaxbyHub swarm-pr-feedback — a skill for ingesting and resolving PR comments, CI failures, and branch conflicts with strict source code verification. CX Codex +1 ★ 539repo stars ce-resolve-pr-feedback EveryInc The ce-resolve-pr-feedback skill judges review comments on a pull request, applies the fixes it approves and closes the conversations. Useful once a PR has piled up feedback. CX Codex +1 3,400installs gitnexus-pr-swarm-review abhigyanpatwari The gitnexus-pr-swarm-review skill splits a pull request review across seven subagents and assembles a production-readiness report. It is built for on-demand PR analysis. CX Codex +1 438installs om-merge-buddy open-mercato om-merge-buddy audits open pull requests against reviews, CI runs, and QA gates to report what can merge right now. Operates purely in read-only mode. CX Codex +1 3,600installs affinage paulnsorensen affinage triages GitHub pull request review comments, CI failures, and merge conflicts. Useful when addressing incoming review feedback on a PR. CX Codex +1 815installs babysit jssblck babysit watches a GitHub pull request until its checks finish, then reports failures, missing checks, and blockers. Use it when CI needs supervised waiting. CX Codex +1 668installs finish-pr PinguApps finish-pr — a skill for Claude Code that guides an open pull request to merge. It fixes merge conflicts, addresses failing CI runs, and resolves reviewer feedback. CX Codex +1 597installs

From the same set121

The whole set →
merge-queue-readiness The merge-queue-readiness skill simulates a PR merged with the latest main before it enters a GitHub merge queue. Use it to catch integration failures that isolated PR checks can miss. CX Codex +1 ★ 539repo stars issue-tracer issue-tracer — a subagent that carries a GitHub issue from report to fix plan. It collects evidence, pinpoints the root cause, and touches no code until you approve the plan. CX Codex +1 ★ 539repo stars qa-reviewer The qa-reviewer subagent reviews pull requests before merge, checking logic, security, error handling, style, and test coverage without changing code. CX Codex +1 ★ 539repo stars durable-session-state The durable-session-state skill keeps task plans, decisions, validation results, and review verdicts in project files. Use it to pick up long-running work after context compaction or a handoff. CX Codex +1 ★ 539repo stars swarm-pr-feedback swarm-pr-feedback — a skill that resolves pull request review comments, CI failures, and branch conflicts through structured verification stages. CX Codex +1 ★ 539repo stars commit-pr commit-pr — a portable skill that verifies your code before push, writes conventional commits, and fills in a PR body. Guards against accidentally committing generated files or secrets. CX Codex +1 ★ 539repo stars test-file-split test-file-split breaks an oversized test file into parts along describe() boundaries when it nears the 500-line cap or blows past it. CX Codex +1 ★ 539repo stars fork-pr-operations fork-pr-operations guides agents through fork pull request workflows: GitHub Actions approval, safe rebasing with force-with-lease, and handling multi-round bot reviews. CX Codex +1 ★ 539repo stars

Project sponsors

Companies that keep this analytics open