JuliusBrussee

JuliusBrussee/caveman

Skill Claude CodeCodex

Build feature work with high overbuilding risk. Use for new behavior, product slices, or integrations where repository reuse, strict scope, and an explicit stop condition matter.

JuliusBrussee/caveman

Skill Claude CodeCodex

Implement reversible compatibility-safe transitions. Use for schema, data, API, protocol, configuration, or dependency migrations requiring rollback and preservation proof.

JuliusBrussee/caveman

Skill Claude CodeCodex

Restructure code while preserving behavior. Use for extraction, consolidation, ownership moves, or cleanup where verification must bracket structural edits.

JuliusBrussee/caveman

Skill Claude CodeCodex

Fix bugs and small behavior changes at the narrowest responsible layer. Use when regression proof, preserved surrounding behavior, and task-relevant tests matter.

JuliusBrussee/caveman

Skill Claude CodeCodex

Prove existing work meets acceptance conditions without expanding scope. Use for validation-only tasks, completion checks, focused gate runs, and last-mile proof.

JuliusBrussee/caveman

Command

Generate a terse caveman-style commit message for staged changes.

JuliusBrussee/caveman

Command

Compress a markdown/text file into caveman format to save tokens.

JuliusBrussee/caveman

Command

Quick reference card for caveman modes, slash commands, and triggers.

JuliusBrussee/caveman

Command

Caveman-style code review — one-line findings with severity.

JuliusBrussee/caveman

Command

Show caveman lifetime token-savings stats.

JuliusBrussee/caveman

Command

Activate caveman mode (lite | full | ultra | wenyan-lite | wenyan-full | wenyan-ultra | off).

JuliusBrussee/cavekit

Plugin Claude Code

Cavekit — compressed spec-driven development for Claude Code.

JuliusBrussee/cavekit

Plugin Claude Code

Cavekit — compressed spec-driven dev. Full loop (grill → spec → research → review → build) over one SPEC.md file: three core commands + four reach-for. Caveman encoding. Bug-to-spec backprop.

JuliusBrussee/cavekit

Command

Plan-then-execute against SPEC.md. Native Claude Code loop, no sub-agents.

JuliusBrussee/cavekit

Command

Drift detector. Diff SPEC.md against code. Read-only, zero writes.

JuliusBrussee/cavekit

Command

Spare-budget design pass. Make one shallow module deep — smaller interface, behavior held, tests green before & after.

JuliusBrussee/cavekit

Command

Sharpen a fuzzy idea into §G/§C before spec. Calibrated interrogation, one question at a time.

JuliusBrussee/cavekit

Command

Gather external knowledge into §R so build grounds in facts, not hallucinations. Every finding cites a source.

JuliusBrussee/cavekit

Command

Adversarial senior review of the spec before build. Refute, don't rubber-stamp. Ends in a go/no-go gate.

JuliusBrussee/cavekit

Command

Create, amend, or backprop bug into SPEC.md. Sole mutator of spec.

JuliusBrussee/cavekit

Skill Claude CodeCodex

Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

JuliusBrussee/cavekit

Skill Claude CodeCodex

Caveman encoding for SPEC.md and spec-adjacent writes. Loaded by /spec, /build, /check. Cuts tokens 75% vs prose while staying precise. Triggers on any write to SPEC.md or when user says "caveman", "compress this", "be brief".

JuliusBrussee/cavekit

Skill Claude CodeCodex

Read-only drift detector. Diffs SPEC.md against current code and reports violations grouped by severity. Writes nothing — suggests remedies via the spec or build skills but never invokes them. Triggers when the user asks to check drift, audit the spec, verify invariants, or ask whether code still matches the spec.…

JuliusBrussee/cavekit

Skill Claude CodeCodex

Optional design-improvement pass for when you have spare usage to drain. Finds the shallowest modules in the code the spec touches, researches a deeper design, and proposes refactors that shrink interfaces and hide decisions — behavior held constant, tests green before and after. Proposes §I/§V/§T edits, never silent…