agent-rig

agent-rig/rig

Agent Claude Code

Tech lead agent for planning, architecture decisions, and ticket creation. Use when breaking down a feature, designing a solution, evaluating tradeoffs, or creating implementation tickets. Invoke before coding begins on any non-trivial change.

agent-rig/rig

Agent Claude Code

Implementation agent for writing production code from tickets or specs. Use when a plan exists and it's time to write code. Reads the ticket, explores the affected files, and implements the change.

agent-rig/rig

Agent Claude Code

Systematic root-cause debugger. Use when investigating a failing test, a production bug, a flaky behavior, or any "this doesn't work and I don't know why" situation. Walks Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix) and refuses to propose fixes before evidence is in.

agent-rig/rig

Agent Claude Code

Test writing agent. Use to write or extend unit tests for new or changed code. Give it the file or function to test and it will produce the test cases.

agent-rig/rig

Agent Claude Code

Code review agent. Use after implementation to check correctness, security, and adherence to project conventions before merging. Provide the diff, PR, or list of changed files.

agent-rig/rig

Skill Claude Code

Systematic root-cause debugging for a failing test, production bug, flaky behavior, or unexplained error. Spawns the debugger agent through Phase 1 → 4 (root-cause → pattern analysis → hypothesis → minimal fix). Refuses to propose fixes before evidence is gathered. Triggers on: 'debug', 'why is X failing', 'root…

agent-rig/rig

Skill Claude Code

Preflight health check for a rig project: detect things that make rig degrade or fail — missing gh auth or the project scope, an unreachable board, an invalid config, no CI gates, missing review catalog — and report each with the exact fix. Diagnose-only by default; --fix applies the safe fixes with confirmation.…

agent-rig/rig

Skill Claude Code

Plan and run a multi-ticket epic: decompose a feature into parent + child items and stack PRs on a shared integration branch instead of landing each on main. Use when children interleave (one item's runtime contract depends on another's incomplete state) — stacking keeps each child PR reviewable without temporarily…

agent-rig/rig

Skill Claude Code

Create, view, move, or manage tickets in the project's issue tracker (Linear, GitHub Issues, or none). Triggers on: 'ticket', 'create ticket', 'move ticket', 'ticket board', 'show tickets', 'list tickets'.

agent-rig/rig

Skill Claude CodeCodex

Onboard the current project into Rig — detect the stack, fill a project profile, and copy in the skills, agents, scripts, and CI workflows you choose. Triggers on 'onboard', 'set up rig', 'install rig', 'adopt these skills', 'onboard me into the skills'.

agent-rig/rig

Skill Claude Code

Turn a written spec or PRD into a reviewed backlog. Reads a spec file, decomposes it into work — deciding per chunk whether it's an epic (interleaved, shared integration branch), a sprint (independent tickets), or a single ticket — shows the plan for approval, then materializes the tickets on the tracker + board with…

agent-rig/rig

Skill Claude Code

Proofread agent-written prose against the project's writing-style guide. find (default): flag buried conclusions, passive voice, hedging, filler, jargon, and unanchored claims in a PR body, ticket, review finding, plan, writeup, or changed Markdown — read-only. fix: rewrite it in place. Triggers on: 'proofread'…

agent-rig/rig

Skill Claude Code needs its repo

Local code review, both halves. find (default): walk the REVIEWER.md catalog + scope invariants against a diff, two adversarial passes, return triaged P0–P3 findings — read-only. fix: drive review feedback to convergence, from a PR review bot OR local find results (spawn coder → recheck until clean). Triggers on…

agent-rig/rig

Skill Claude Code

Run a time-boxed research spike to answer an open technical question or de-risk an approach BEFORE committing to implementation. Produces written findings + a recommendation (and optionally a throwaway prototype), not production code. Use when the team needs to evaluate feasibility, compare options, or reduce…

agent-rig/rig

Skill Claude Code

Plan or run a sprint of independent tickets (or ad-hoc tasks). Use 'plan ' to decompose a feature into independent tickets (no integration branch — each lands on the trunk on its own). Pass ticket IDs (or task descriptions) to execute them in phased dependency order with cleanup between phases. With no args (or just…

agent-rig/rig

Skill Claude Code

Implement one unit of work end-to-end — from a tracker issue OR an ad-hoc description: spec review, TDD (RED→GREEN→REFACTOR), pre-PR self-review, open a PR, then drive the review-bot loop to clean. Runs start→finish in one shot by default; start/finish are optional phases for pause/resume. Sibling to /rig-epic (one…

agent-rig/rig

Skill Claude Code

Run post-merge code cleanup: audit recent changes for dead code, duplicates, and stale comments, then safely remove them. Triggers on: 'cleanup', 'simplify', 'clean up code', 'remove dead code', 'post-merge cleanup'.

agent-rig/rig

Skill Claude Code

Manage isolated git worktrees: create one wired up for dev (fetch, branch from base, symlink env, install deps), list them with PR state, or safely remove merged ones. A shared bootstrap that implement-style flows can call, also usable directly. Triggers on: 'worktree', 'set up a worktree', 'new worktree', 'list…