drn

drn/dots

Skill Claude CodeCodex

Open Plannotator on the latest rendered assistant message and use the returned annotations to revise that message or continue.

drn/dots

Skill Claude CodeCodex

Open Plannotator's browser-based code review UI for the current worktree or a pull request URL, then act on the feedback that comes back.

drn/dots

Skill Claude CodeCodex

Create reviewed Codex goal setup packages for long-running /goal work. Use when the user wants to turn an idea, backlog, project mission, or vague objective into durable goal files under a project goals slug folder, with Plannotator review gates for brief, narrative plan with acceptance criteria, verification…

drn/dots

Skill Claude CodeCodex

Generate self-contained HTML visualizations with Plannotator theming. Use for implementation plans, PR explainers, architecture diagrams, data tables, slide decks, and any visual explanation of technical concepts. Plans and PR explainers follow Plannotator's prescriptive approach; all other visual content delegates to…

drn/dots

Skill Claude CodeCodex

Analyze codebase for code smells and refactor to drastically improve code quality. Expert in clean code, SOLID principles, Ruby patterns, service objects, and refactoring. Use for code quality audits, refactoring sessions, and cleaning up technical debt.

drn/dots

Skill Claude CodeCodex

Open a PR, wait for CI to pass, fix failures, address review comments, and loop until fully green. Use when opening a PR, fixing CI, or addressing review feedback.

drn/dots

Skill Claude CodeCodex

RICE-scored backlog prioritization. Use for sprint planning, feature prioritization, or backlog grooming.

drn/dots

Skill Claude CodeCodex

Summarize the prompts used in the current conversation as a numbered list. Use when the user wants to see the prompt chain, review their prompts, or share the sequence of prompts that produced a result.

drn/dots

Skill Claude CodeCodex

Clean up merged and stale git branches, prune old local and remote branches safely. Use for cleaning up old branches or pruning stale remotes.

drn/dots

Skill Claude CodeCodex

Rebase current branch onto latest upstream default branch and force-push to update PR. Use when updating a branch, rebasing onto main, or resolving conflicts.

drn/dots

Skill Claude CodeCodex

Create a versioned release with changelog generation, git tag, and GitHub release. Use for creating releases, tagging versions, or publishing changelogs.

drn/dots

Skill Claude CodeCodex

Iteratively run /rereview, fix the findings, and loop until reviewers approve clean. Use for iterative automated review, when you want /rereview to loop until clean, or for a paranoid pre-merge review that auto-addresses every blocker.

drn/argus

Hook Claude Code

Runs before the agent uses a tool for Bash tool calls, running an inline shell check. From drn/argus.

drn/argus

Settings file Claude Code

Agent settings declaring 1 hook event (PreToolUse).

drn/argus

Skill Claude CodeCodex

Archive the current Argus task so it moves to the Archive section of the task list. Use at the end of a session when the work is done.

drn/argus

Skill Claude CodeCodex

Mark the current Argus task as complete. Use when the work for the current worktree is done and the user wants the task to transition to the "complete" status.

drn/argus

Skill Claude CodeCodex

Manage recurring or one-shot tasks in the local Argus daemon via its HTTP API. Use when the user wants to schedule a task locally in argus, create a cron-driven task, fire X every weekday/hour/morning, fire something once at a specific future time (one-shot via runonceat), set up an agent that needs local filesystem…

drn/argus

Skill Claude CodeCodex

The hera plan-DAG: author staged, dependency-ordered multi-worker plans inside an argus sandbox and let the daemon gater materialize each node into a born-bound worker as its blockers finish. Load this (in addition to the base hera skill) when you are a coordinator and the work decomposes into multiple hera worker…

drn/argus

Skill Claude CodeCodex

Corrective review lens: interrogates the tests touched or added by a diff for false confidence, instead of reviewing the diff broadly for correctness (that's hera-review's job). Trusting a green test run is a systematic blind spot broad finders share — codex's blind spot #2 specifically (see…

drn/argus

Skill Claude CodeCodex

Default, user-overridable code review methodology — the review CONTRACT (what to analyze, how to tag findings) that a broad finder follows when spawned inside a hera-spawn-review panel, or that runs standalone via /hera-review for a single-pass review outside a panel. Encodes ralph-review's review contract (behavior /…

drn/argus

Skill Claude CodeCodex

Orchestrate a vendor-diverse review panel over a diff: resolve the project's diligence-profile [panel] via mcpargusprofileresolve, spawn each broad finder and corrective lens as an in-session Claude sub-agent injected with its configured review instruction, synthesize every finder's output into the canonical finding…

drn/argus

Skill Claude CodeCodex

Inside an argus sandbox (cwd under /.argus/worktrees/ or ARGUSTASKID set), coordinate multi-agent work via hera's mcpargushera tools — bootstrap an orchestrator, claim or attach a worker/freelance role, spawn workers, and message roles over the idle-gated bus. Load this skill when you are (or are becoming) a…

drn/argus

Skill Claude CodeCodex

Resolve a diligence profile's per-archetype model (and, where the dispatch mechanism accepts it, effort) for Claude's NATIVE sub-agent dispatch (the Agent/Task tool, or Workflow's agent()) — as opposed to hera worker spawn, which already gets this via internal/agent.ResolveModel. Use when a coordinator or pipeline…

drn/argus

Instructions file

Claude Code instructions for drn/argus, covering claude.md, what this is, spec-driven development (openspec), build & run and before opening a pr.