swarm-pr-review

swarm-pr-review is a skill for Claude Code, Codex from ZaxbyHub/opencode-swarm. It costs 91 tokens per session (22,726 once invoked), scanned A, original, MIT.

A structured pull-request review process that combines automated signals, independent reviewers, and a final challenge of proposed findings.

In plain words
What is it for?
Reviewing pull requests, validating findings, grouping feedback, recording review results, and handing confirmed issues to a follow-up workflow.
Why use it?
It helps distinguish real defects from unverified concerns while covering common risk areas in a change.

Skill for Claude CodeCodex

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/zaxbyhub/opencode-swarm/baseline
Any agent
npx skills add ZaxbyHub/opencode-swarm --skill baseline
Clone the repo
git clone --depth 1 https://github.com/ZaxbyHub/opencode-swarm

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.

agentmods badge for swarm-pr-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/baseline.svg)](https://agentmods.dev/skills/zaxbyhub/opencode-swarm/baseline)
Your own site
<a href="https://agentmods.dev/skills/zaxbyhub/opencode-swarm/baseline"><img src="https://agentmods.dev/badge/skills/zaxbyhub/opencode-swarm/baseline.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 22,726 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 $0.00091 $0.22726
Opus 5 $0.00046 $0.11363
Sonnet 5 $0.00018 $0.04545
Haiku 4.5 $0.00009 $0.02273

Measured yesterday against content hash 1bcee0a5fe06, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

swarm-pr-review 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 yesterday.

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.

evaluation-fixtures/pr-review-recovery/baseline/SKILL.md · 1,824 lines

How it starts

The opening of the file, as written. The whole thing — 1,824 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/swarm-pr-review

Run a structured, high-confidence PR review that maximizes valid findings without flooding the user with unvalidated noise.

The review ladder is:

Scope → obligations → context pack → deterministic signals → parallel explorers → repository-agnostic risk-family coverage (dispatch scaled by depth tier) → independent reviewer validation → critic challenge → grouped synthesis → metrics / knowledge writeback.

Handoff To PR Feedback

Use ../swarm-pr-feedback/SKILL.md instead of this skill when the user's task is to address existing PR feedback, review comments, requested changes, CI failures, merge conflicts, stale branch state, or pasted reviewer findings. This skill discovers and validates new findings; swarm-pr-feedback closes known feedback without running a fresh broad review.

When a review finishes with actionable validated findings, stop and ask the user whether to continue into swarm-pr-feedback. Do not auto-dispatch fix work from PR_REVIEW. Instead, write a handoff artifact — under Profile A, .swarm/pr-review/<run_id>/feedback-handoff.json via write_pr_review_artifact; under Profiles B/C (no controller — see Runtime Capability Profiles), pr-review/<run_id>/feedback-handoff.json inside your session/task workspace, never under .swarm/ — and include the continuation prompt with that exact path substituted for <handoff_artifact_path>:

/swarm pr-feedback <PR_URL> continue from <handoff_artifact_path>

<run_id> is a stable identifier for this review run, such as pr-<number>-<YYYYMMDDHHMMSS> or the existing review artifact run ID when one was already created. Under Profile A, the exact command is parsed mechanically: the controller validates the terminal review, the bounded handoff artifact, and its provenance before atomically replacing the review gate with an unbound feedback gate. Extra trailing text is not permitted on this continuation form. Profiles B/C ingest their task-workspace artifact through the skill-managed path.

Read the full file on GitHub · 1,824 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.

  1. yesterday First seen · 1,824 lines · 91 tokens per session scan A 1bcee0a5fe06

Subscribe to this mod's changes

swarm-pr-review is a skill published in the GitHub repository ZaxbyHub/opencode-swarm (462 stars, last pushed today), licensed MIT. It adds 91 tokens to every session and 22,726 once invoked, about $0.0005 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 2026-09-03.

Related

Other skills, from other repositories

ux-create-manifest

Create the initial Product UX Bible for an existing web or full-screen web app by deeply auditing the repository, using sub-agents when available, and generating docs/ux manifests, schemas, budgets, surface maps, action taxonomy, and design-token policies from observed code.

h0x91b/dev-3.0 · 58 tokens

ux-principal

Principal UX architect skill for deciding WHERE a UI feature belongs, before it is implemented. Reads and maintains docs/ux manifests, classifies the feature, decides placement, navigation, surface, action hierarchy and complexity budgets, and produces a precise implementation brief without coding unless explicitly…

h0x91b/dev-3.0 · 87 tokens

verify-changes

How to test and verify work in the dev-3.0 repo — which vitest config covers what, how to write a test that fits the house style, mocking Electrobun RPC and i18n providers, what coverage is actually expected, and the browser QA hand-off. Use when writing or fixing tests, deciding what a change needs covered, hitting a…

h0x91b/dev-3.0 · 124 tokens

debug-ui

Drive and visually QA the dev-3.0 UI in a real browser (headless Chromium via agent-browser). Use when verifying a UI/UX change, reproducing a visual bug, taking screenshots of the running app, or self-QA before review. Triggers — "check the UI", "screenshot the app", "does this render", "QA this screen", "verify the…

h0x91b/dev-3.0 · 93 tokens

zhihu-publish

Use when the task is to publish a Zhihu article from Markdown using the local browser-automation pipeline in this repo. Covers the text-only publishing chain, the multimodal chain that uploads Markdown images into the Zhihu editor, cookie-based login checks, and choosing between the stable text script and the richer…

Harzva/learn-likecc · 69 tokens

full_unpackd_rep

Use when the task is to unpack a local reference repository into a Chinese structural topic page, update site navigation, stamp dates, and leave behind a reusable deconstruction note for the repo.

Harzva/learn-likecc · 42 tokens