Review the diff while you code: a panel of focused review lenses, a second-model review (Codex, Claude or open-code-review), and hooks that nudge a review every few commits and after a large edit. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
Plugin review from marketplace agentic-workflow-kit in tetriz-ai/agentic-workflow-kit. Commands read from the repo's manifest — 12 days ago.
This plugin runs code on your machine — its hooks fire automatically on events like tool use. The exact commands are listed below; read them before installing.
claude-lensRuns a local, read-only adversarial review of the current branch's committed changes with Claude, using the model and effort from the review plugin's settings. Use for /review:claude-lens, for a second opinion from Claude, or as the review panel's automatic counterpart when Codex wrote the change. T
codex-lensRuns a local, read-only adversarial review of the current branch's committed changes with Codex, using the model and reasoning effort from the review plugin's settings. Use for /review:codex-lens, for a second opinion from Codex, or as the review panel's automatic counterpart when anything other tha
harness-educationMines merged pull requests and their review threads for lessons worth keeping, and shows them as a table of candidates. A human picks which to keep, and only those ship, as a separate pull request for review. Nothing is added on its own. It runs only when the user invokes /review:harness-education.
ocr-lensRuns a local, read-only adversarial review of the current branch's committed changes with open-code-review, a model of a different lineage, through the gateways and model in the review plugin's settings. Use for /review:ocr-lens, or as the review panel's extra engine next to the automatic Codex or C
review-panelReviews the diff so far with fresh subagents, one per lens, and grades findings Critical, Important or Minor. Use during coding when the review-cadence hook nudges, and once before a PR (pre-pr). A second model reviews the same range through /review:codex-lens or /review:claude-lens. Findings never
"${CLAUDE_PLUGIN_ROOT}"/scripts/hook-once.sh review-cadence.sh
"${CLAUDE_PLUGIN_ROOT}"/scripts/hook-once.sh self-check.sh
Open and maintain pull requests: the pr skill, PR writing style, all-surfaces PR feedback, the Codex review sweep, GitHub issues, and PR-description drift nudges. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
5 skills · hooks
Tech design docs (RFCs) written fork by fork, their review, task breakdowns into shippable slices, and ADRs. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
4 skills
Ship work unattended between gates: one task, a whole label queue, or a bug hunt, each fix through the merge gate and the review panel to a pull request. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
3 skills · hooks
Set up a repo for the kit: the setup skill writes the settings file, the deny list, the always-on rules, githooks and the rule index; a short guide maps situations to skills. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
2 skills · hooks
Hooks around an agent's commands and edits: a configurable commit gate, a lockfile sync gate, pinned npx, format on edit, and generated-file and doc-health advisories. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
hooks
Extracts an abstracted profile of how you work with an agent, scrubbed for credentials, and shares it as a pull request. Tested on Claude Code 2.1.289+ and Codex CLI 0.159.0+.
1 skill
Matt Pocock's agent skills for real engineering (grilling, spec/ticket flows, TDD, code review, domain modelling and more).
39 skills
Core skills library for Claude Code: TDD, debugging, collaboration patterns, and proven techniques
15 skills · hooks
Open-source AI job search that runs locally in your AI coding CLI: scan job portals, evaluate listings into a structured A-H report with a 1-5 score, tailor your CV, track applications
5 skills · hooks
Up-to-date documentation lookup. Pull version-specific documentation and code examples directly from source repositories into your coding agent's context.
1 MCP server
Build powerful, stateful CLI interfaces for any GUI application using the cli-anything harness methodology.
5 commands
5 skills + 35 modes + Material Passport pipeline. Includes v3.6.7 cross-model audit gate and v3.6.8 generator-evaluator contract.
5 skills · 16 commands · 4 agents · hooks
This page updates itself from your repo. Add the badge to your README, or get it Featured to pin it above the organic results with a followed link to your site.