laicluse-agent-fieldkit

Capture friction with /fuck, /fucking, /fucked, /shit, /crap, /wtf, or /bullshit for later background investigation. Fix now with /safeword, /pineapple, /pineapplejuice, /pinapplejuice, /flugelhorn, or /banana. /anger-management:repair reviews captured notes and applies or routes high-confidence fixes; /anger-management shows the tally. State stays local.

15 skills

Parallel-worktree Git flow, repo-aware push policy, atomic verified merges, and commit/push hooks for agent sessions and direct CLI use.

14 skills · hooks

Execute bounded autonomous missions with evidence, independent review, explicit stop conditions and honest negative outcomes. Supports continuation, preparation, verification and focused subtraction review.

8 skills

Guardrail hooks plus explicit commands: /duh executes the previous proposal, /just-a-question keeps a turn read-only, /not-your-monkey inspects visual work, and /then defers a prompt until the current turn ends. Supports Claude Code and Codex.

4 skills · hooks

Improve visual and interaction design: clarify confusing UI, explore visual treatments, establish product identity, and review actual rendering against accepted references.

5 skills

Review software, decisions, and writing through opinionated panels. Claude and Codex receive host-specific review workflows; Claude also receives the sonnet-max panel agent.

4 skills · 1 agent

Apply chosen conventions for naming, testing, programming, removing superseded residue, and keeping authoring context out of artifacts. An opinionated baseline among defensible alternatives.

5 skills

Get an independent peer review of recent work or a design: Claude consults Codex, and Codex consults Claude, with explicit model choices and follow-up on disagreements.

4 skills · hooks

Keep autonomous missions running across turns with a host capability probe, heartbeat backoff, auto-stop, and wake/restore where needed. Persistent hosts need no heartbeat machinery.

3 skills

Create worktrees from the freshest default branch, set them up from `.bonsai` files, and safely remove finished worktrees while preserving unintegrated work.

3 skills

Claim, check, and release directory occupancy locks so coding agents do not mutate the same checkout concurrently. Vendor-neutral CLI with live-holder protection and stale-lock recovery.

2 skills · hooks

Build and diagnose plugins, skills, and marketplaces across Claude and Codex: naming, invocation, generated adapters, sync, and installed-cache freshness.

3 skills

Reach beyond a first answer: research before choosing (inspire), verify doubtful claims (ground), and reconstruct drifting projects from first principles (rethink). Skills: inspire, ground, rethink.

3 skills

One source of truth for shared and agent-specific instructions, project-level CIRCUS.md sync, Codex plugin adapters, and marketplace versioning across coding agents.

2 skills

Find duplicated logic and parallel paths in code, prose, or design. Run a quick scoped check or a whole-codebase parity audit, then converge verified divergence and check the result.

2 skills

Automatically commit and verify Markdown vault changes locally, then rebase and push when an upstream exists, with conflict handling and Dibs coordination.

1 skill · hooks

Copy the core of the last answer to the macOS clipboard, as plain text or Slack-compatible rich text.

1 skill

Read the latest marketplace or installed-plugin CHANGELOG news with whats-new, without changing post-update broadcast state.

1 skill

Local-first Pattern Memory for reusable implementation recipes. Stores personal patterns as Markdown and keeps private precedents out of public artifacts.

1 skill

Speak agent responses aloud on macOS, translating screen content into spoken language rather than reading it verbatim. Includes on/off commands, a phonetic dictionary, and serialized playback across sessions.

1 skill

Routes user feedback about agent behavior to the strongest durable target: hooks, skills, project code, or instruction files.

1 skill

Explore a goal, root cause, or unclear decision through repeated why-questions, then analyze the chain for a better direction.

1 skill