4,217 tagged developer-tools, measured the same way as everything else here.
Browse within: ai-assistant 120ai-workflow 95documentation 91coding-agents 77hooks 67code-quality 64prompt-engineering 61workflow 61agentic-coding 59knowledge-management 58azure-devops 52spec-driven-development 50claude-code-plugins 46context-management 43
Command
A command that guides a raw product idea through a structured process ending in a product requirements document and a clickable HTML prototype. A product requirements document describes what a product should do and why.
Command Claude Code
Land every unshipped set on main as its own patch release, then leave a clean tree.
jens-duttke/usage-monitor-for-claude
Command Claude Code
Analyze the staged changes by running git diff --cached and the current branch name by running git branch --show-current, then generate a commit message according to the following rules.
jens-duttke/usage-monitor-for-claude
Command Claude Code
Maintainer pre-merge gate - audit a PR (or staged changes), output review comments, then CHANGELOG entry.
jens-duttke/usage-monitor-for-claude
Command Claude Code
Cut a new release - bump the version, roll the changelog, and prepare the GitHub release notes.
Command
Install the claude-pace statusline bundled with this plugin.
Command
Second-model review. Picks an auditor (codex/gemini/opencode/aider/copilot), excludes the caller, writes a prompt to paste, reads the response back. Usage: /cross-audit [--with | list | compare].
Command
Adversarial multi-angle critique. All three auditors fire in parallel (codex=technical, gemini=strategic, claude=ux). Counter-args ranked by rebuttal survival score, not raw severity. Usage: /cross-critique [--with | list | compare].
Command
Two-phase multi-model research. Phase A fans codex+gemini in parallel (benchmarks + citations angles); Phase B synthesises via fresh Claude session. Usage: /cross-research [--with | list | compare].
Command
Use Codeflow as the proof-and-replay layer around the current task.
Command
Update nanostack to the latest version.
Command Cursor
Run npm run scan from the repository root. This repo must report L4 · Self-correcting.
Command Cursor
Review the current diff for violations of the conventions in AGENTS.md and .cursor/rules/. Report findings ordered by severity; do not fix anything unless asked.
Command
Audit this repository's AI harness maturity with the deterministic harness-score scanner.
Command
Finish a PR properly: every check green, every review addressed — human and bot — then merge and clean up.
Command
Prepare and open a pull request the senior way: gate, template, scrubbed, everything visible.
Command
Spec-first design: a gap-closing interview that produces a complete spec, with a quality controller that blocks until every section is answered and every question resolved.
Command Claude Code
You are orchestrating a Plan → Implement → Review → Remediate → PR cycle for a GitHub issue, with support for stacked PRs when issues form a linear dependency chain.
Command
Handle CodeRabbit AI review cycles after creating a PR.
Command
Think through a problem on paper before acting.
Command
Start a work-until loop that keeps you working on a task until completion.
Command
Command "call" from The-17/agentsecrets, covering agentsecrets call, usage, description, options and examples.
Command
Command "env" from The-17/agentsecrets, covering agentsecrets env, usage, makefile integration, pattern 1: run prefix variable (recommended) and pattern 2: named targets (explicit).
Command
Command "project" from The-17/agentsecrets, covering agentsecrets project, subcommands, project list, project create and project: my-backend (projabc123).