agent-patterns-plugin

Plugin agent-patterns-plugin from marketplace laurigates-claude-plugins in laurigates/claude-plugins. Commands read from the repo's manifest — today.

Skills (24)

• adversarial-review

  Adversarial second-pass review that tries to break code, designs, plans, or ADRs. Use when stakes are high and a normal review already ran.

• agent-cli-worktree-safety

  Data-loss invariants for a CLI that runs an agent SDK in a git worktree then force-removes it. Use when building or reviewing such a CLI, or when an agent run reports "no changes" after writing files.

• agent-teams

  Configure Claude Code agent teams (implicit team, SendMessage, TaskUpdate). Use when running parallel agents, coordinating with messaging, or setting up a lead/teammate architecture.

• cold-read-gate

  Gate outward-bound text (upstream issues, docs, PR bodies) through isolated haiku fresh-reader critique before publishing. Use when an artifact must survive a reader with zero project context.

• custom-agent-definitions

  Write and configure custom agent definitions in Claude Code agents/ directory. Use when creating an agent .md file, defining a specialized agent, or configuring agent tools.

• exclusive-lock-dispatch

  Pre-dump-then-dispatch for tools holding an exclusive lock (Ghidra, migrations, single-writer caches). Use when fanning out parallel agents needing a non-concurrent resource.

• execution-grounded-review

  Execution-grounded review: run tests first, trace each acceptance criterion to execution evidence. Use when verifying an implementation meets spec.

• expose-tunable-knob

  Expose a live-adjustable control instead of guessing a magic constant for a parameter the agent cannot itself perceive. Use when tuning visual, audio, or UX output (color, size, position, timing, volume) that only the user can judge.

• harness-tool-errors

  Claude Code harness tool errors — Read on a missing path, directory or oversized file; Edit before Read or after a formatter; Bash permission denials. Use when a Read, Edit, Write or Bash call errors.

• mcp-code-execution

  Scaffold the code execution pattern for MCP-based agents. Use when agents call many MCP tools, intermediate data exceeds context, you need loops, or PII must stay out of context.

• mcp-management

  Install, configure and troubleshoot MCP servers. Use when adding/enabling servers, editing .mcp.json, fixing OAuth, or when a server runs stale code after an upstream fix.

• mcp-server-authoring

  FastMCP authoring for Python MCP servers — tools, resources, prompts, TDD, release-please. Use when building or extending an MCP server, adding a tool/resource, or scaffolding a new server.

• meta-assimilate

  Copy, generalize, or merge a project's .claude/{agents,commands} into user-scoped configuration. Use when assimilating another project's Claude setup or generalizing an agent.

• meta-audit

  Audit Claude subagent configs for completeness, security, and best practices. Use when reviewing agents/ for missing frontmatter, overprivileged tools, or bad model choices.

• meta-context-diet

  Audit CLAUDE.md and .claude/rules for always-loaded content that should become an on-demand skill. Use when CLAUDE.md feels bloated, trimming context, or promoting a rule into a skill.

• meta-local-notes

  Audit a CLAUDE.local.md — verify each claim live, fix drifted environment facts, cut findings duplicating versioned docs. Use when local notes are stale, or before appending a finding.

• meta-promote

  Promote rules, skills, or agents from project scope to parent or user-global scope. Use when reorganizing .claude/ directories or when sibling repos hold near-duplicate rules.

• multi-model-delegation

  Multi-model design consults via PAL (kimi, glm, gemini, gpt). Use when asking other models to brainstorm a design or reconciling their split answers.

• parallel-agent-dispatch

  Dispatch contract for spawning parallel agents covering worktree collisions, scope overflow, and silent exits. Use when fanning out concurrent agents or authoring a lead prompt.

• plugin-settings

  Configure per-project plugin settings via .claude/plugin-name.local.md files. Use when building plugins with user-configurable behavior, storing agent state, or controlling hooks.

• probe-input-integrity

  Take probe identifiers from the system, run a known-good control, extract (never retype) the code under test, make stubs executable. Use when probing an endpoint, id, path or test harness.

• tool-result-traps

  Tool results that mean something other than they look — a pattern that never compiled, a glob that cannot match a directory, one tier searched but reported absent, a rejected flag reading as "no results". Use when an empty result is about to gate an action, land in a doc, or be reported as done.

• verify-before-plan

  Verify orchestrator premises (file counts, build state, artefact presence) before dispatching parallel subagents. Use when a wave's briefs cite a number, path, or behaviour not yet checked.

• wave-based-dispatch

  Sequential-wave dispatch for WO chains where output of one feeds the next, shared locks, or shared files prevent fan-out. Use when planning dependent multi-WO landings.

Similar plugins