conn-castle

conn-castle/agent-layer

Skill Claude CodeCodex

First command description.

conn-castle/agent-layer

Skill Claude CodeCodex

Second command does something useful for testing wrap lines in codex skills.

conn-castle/agent-layer

Settings file Claude Code

Agent settings declaring 4 allowed tools.

conn-castle/agent-layer

Instructions file GitHub Copilot

Instructions for conn-castle/agent-layer, covering base and extra.

conn-castle/agent-layer

MCP server Claude CodeCodexCursor +2

MCP server "agent-layer" as configured in conn-castle/agent-layer. Launched with /bin/sh -c AL_MCP_WORKING_DIR=$PWD; export AL_MCP_WORKING_DIR; cd "$1" && exec a.

conn-castle/agent-layer

MCP server Claude CodeCodexCursor +2

MCP server "example", hosted remotely at mcp.example.com, as configured in conn-castle/agent-layer.

conn-castle/agent-layer

Skill Claude CodeCodex

Use Agent Dispatch MCP tools only when the user names an external dispatch target or another skill explicitly requires dispatch. Do not use it for generic subagent, second-agent, or fresh-context requests; use the built-in subagent instead.

conn-castle/agent-layer

Skill Claude CodeCodex

Use globally installed ctx7 for API/library docs when local docs or CLI help are insufficient. Trigger for API syntax, config, setup, migrations, version-sensitive, or post-cutoff questions. Do not use for web research, local files, browser automation, or installs.

conn-castle/agent-layer

Skill Claude CodeCodex

Use globally installed playwright-cli for browser automation, UI inspection, screenshots, Playwright test debugging, or test generation. Trigger when a task needs browser interaction or test repair. Do not use for generic tests, web search, non-browser docs, or API-only work.

conn-castle/agent-layer

Skill Claude CodeCodex

Manage local skills backed by known remote Git repositories. Use when the user wants to import, inspect, diff, pull, resolve, push, reset, or remove them, or project current local skills to enabled clients with al sync. Do not use to discover new skills or create user-owned skills.

conn-castle/agent-layer

Skill Claude CodeCodex

Use Tavily CLI for web search, URL extraction, site mapping, and cited research. Trigger when the user needs current web info, asks to search/read a page, provides URLs, or wants a sourced report. Do not use for browser automation, local docs, or Tavily setup.

conn-castle/agent-layer

Skill Claude CodeCodex

Audit Markdown docs for static accuracy and cross-document consistency against the repo, fixing what is safe. Excludes memory files by default.

conn-castle/agent-layer

Skill Claude CodeCodex

Audit agent memory files (ISSUES, BACKLOG, DECISIONS, COMMANDS, CONTEXT) for structure, staleness, placement, consistency, and DECISIONS.md bloat; fix accepted findings.

conn-castle/agent-layer

Skill Claude CodeCodex

Audit the existing test suite once for redundancy, misleading coverage, organization, and material behavioral gaps, directly fixing safe findings.

conn-castle/agent-layer

Skill Claude CodeCodex

Run an autonomous loop intended to result in merged PRs.

conn-castle/agent-layer

Skill Claude CodeCodex

Implement a large, substantive code change directly or through a planned cross-agent workflow, adding plan or code review only when warranted.

conn-castle/agent-layer

Skill Claude CodeCodex

Audit product interfaces as component boundaries, score complexity, over-engineering, and debt, maintain .agent-layer/tmp interface-audit reports, and finish at the final recommendation gate. Use for fresh interface cleanup audits or --update refreshes; not for implementation.

conn-castle/agent-layer

Skill Claude CodeCodex

Ship one pull request, monitor hosted CI and review feedback, follow PR policy, and request authorization before merging and cleaning up.