Hostile, bias-free review of a change — dispatches independent adversarial reviewers that hold the code against what was agreed and question whether what was agreed was right, plus a standalone false-positive filter, and reports only verified findings in plain language. Ships a full 18-reviewer panel, a cheaper quick panel that proposes the fewest reviewers that fit the change, lets you add or drop any, and keeps both verification gates, and a fast one-reviewer review that checks its own findings and re-checks only what changed since the last review.
3 skills
Keeps what the agent makes from reading as AI slop, in two skills. anti-slop-ui covers interfaces: no gradient-everything, rainbow palettes, pulsing badges for states that never change, fingernail-striped cards, emoji icons, default fonts, uppercase labels, scroll effects, screens with no hierarchy or no empty, loading, and error states, or landing-page hype on working screens. anti-slop-text covers prose: no invented details, inflated significance, promotional tone, weasel attributions, not-X-but-Y contrasts, manufactured rhythm, AI vocabulary, chat residue, restating conclusions, or PR text about what was left unchanged. Each checks its output against a catalog of known tells before it ships.
2 skills
Fully local visual plans and recaps — the agent writes markdown, a bundled zero-dependency server renders it in your browser with Mermaid diagrams, rich diffs, styled DB migrations, API call cards, and a read-only OpenAPI view, with live reload and a comment feedback loop. No remote services.
2 skills
Comment discipline for code the agent writes — every comment stays within a line or two, carries information the code does not, and describes the current state only, with no iteration labels, finding numbers, wave or task IDs, project phase names, or narration of how the code got here; regressions are pinned by tests instead.
1 skill
Re-asks the questions an agent has open, one per chat message, in one fixed shape — a numbered claim, the situation, a numbered flow to the consequence, the fix, its cost, your call — after checking the facts and that each recommended fix really works, and builds nothing until every question has a direct apply, reject, or different direction. After a doubtful reply it asks the user to say which they mean. Never uses the harness question tool.
1 skill
Language-agnostic code simplification — reduces complexity (nesting, long functions, duplication, dead code, unclear names) while preserving exact behavior, applying one tested change at a time within a deliberate scope.
1 skill
Plain-language communication for readers who can't see the code — the agent translates findings, answers, status, plans, and recaps out of file/function/variable names into Simplified Technical English (ASD-STE100), leads with the outcome, keeps the important point in the final message of the turn, and matches technical readers only when they ask.
1 skill
Opinionated Go writing discipline — idiomatic Go from Effective Go, the Google style guide, the Go Proverbs and the Gruntwork guide, with a stated house preference for natural-language, wrappable error messages, hand-written Fn-field mocks that fail loudly, comment and simplification discipline folded in, and a per-change checklist the agent runs before calling Go code done.
1 skill
Hands-free implementation of an agreed plan — worktrees and cheap-model executors under TDD, an item-by-item conformance check against the plan on the premium model, an adversarial review sized to the change (installed skills or an on-the-spot panel), technical decisions logged and functional ones left to the user, a capacity check and /goal condition up front, and no worktree deleted without asking.
1 skill
Plan-building flow that ends in one clean plan, never a story of revisions — a commit-stamped map of the codebase's structure, flows, patterns, and tests, parallel exploration, a zero-context review of the draft against the original ask, questions batched for the user and filtered by what was already decided, tickets with what/why/acceptance criteria/dependencies/size, spikes resolved on the spot, every decision logged with its reason, and a plain-text handoff to implementation.
1 skill
A quick plan for a small coding change — one short plan file with one ticket, the repository's patterns and the tests to extend found by two scoped explorers instead of a full codebase map, unknowns checked on the spot, only the user's decisions asked, one fresh check of the plan, and a warning whenever the change outgrows a quick plan, recommending the full planning-flow skill when it is installed.
1 skill
Docs-first discipline for anything involving third-party APIs, packages, providers, or fast-moving product behavior — the agent web-searches for current official docs and reads primary sources before assuming from memory, grounding answers in what the docs actually say.
1 skill
End-of-session recap that reports the result, not the journey — was the original ask met, what now works in plain words, the decisions the agent made on the user's behalf, the side effects and open decisions the reader must act on, and what was verified — written in Simplified Technical English (ASD-STE100) for a reader who never saw the code, with no detours, reverts, or internal names.
1 skill
Budget loop for long-running or parallel agent work under Claude's 5-hour and weekly usage limits — run bounded waves, check real usage between them, pause before the cap, and resume with self-contained prompts only when the window is actually clear.
1 skill
Run expensive top-tier models (Claude Fable/Opus, GPT-5.6 Sol, or similar) efficiently — the premium model keeps judgment, architecture, synthesis, and final review, while cheaper subagents (Sonnet, Haiku, Terra, Luna) do bounded token-heavy research, coding, and testing with self-contained handoffs and verified results.
1 skill
Installs every plugin in this marketplace in one step. It has no skills of its own; it lists the other plugins as dependencies, and Claude Code installs and enables each of them. Claude Code only — Codex has no plugin dependencies.