Fuse Claude with the Codex CLI: Watchdog auto-reviews each turn, Duel Plan co-plans with debate, Duel Review reviews a PR with two agents, Consult fetches a second opinion.
Plugin fusion-harness from marketplace pronskiy-skills in pronskiy/skills. Commands read from the repo's manifest — 28 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.
consultUse when you want an independent second opinion from the Codex CLI on a specific decision, design, bug, or piece of code — triggers like "ask Codex", "what would Codex say", "get a second opinion", "cross-check this with another model", "have another agent look at this". One-shot and read-only. Requ
duel-planUse when planning a non-trivial change and you want two agents to plan it adversarially before any code is written — Claude and the Codex CLI each draft a plan, debate it, and converge into one. Triggers like "duel plan", "plan this with Codex", "have Claude and Codex argue out a plan", "co-plan thi
duel-reviewUse when you want two agents to review a pull request and challenge each other before you act on it — give a PR link (or number/branch) and Claude and the Codex CLI each review it independently, then debate the findings. Triggers like "duel review", "duel review this PR", "have Claude and Codex revi
/fusion-harness:watchdogTurn the Codex Watchdog (auto-review on each finished turn) on or off for this project
${CLAUDE_PLUGIN_ROOT}/scripts/watchdog-stop.sh
Rewrites a prompt to be more ambitious through Altitude (the outcome behind the task), Depth (raw material, a professional's instruments, an outside judge) and Range (methods from other fields), after Felix Rieseberg's post, and returns one rewritten prompt. Runs only as /reprompt.
1 skill
Check writing for the tells of AI-generated text, surface and structural, and report each with the quoted span, category, and fix, or return a de-slopped rewrite.
1 skill
Interview the user about a project, then produce a production-ready SPEC.md (plus CLAUDE.md and an optional private spec).
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
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
Perform AI code review on Git diffs — supports workspace changes, branch ranges, and single commits with concurrent per-file analysis, codebase search, and deep context-aware review.
2 commands
Backend API design, GraphQL architecture, workflow orchestration with Temporal, and test-driven backend development
9 skills · 1 command · 8 agents
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.