메뉴
Launch FoxCode in Project Profile mode via the foxcode MCP server (`launchBrowser` tool). One tool call, no Python.
Codex 또는 Claude로 설치 이 Prompt를 복사해 Codex, Claude 또는 다른 어시스턴트에 붙여 넣으면 Skill 페이지를 검토하고 설치를 진행할 수 있습니다.
SOC 직업 분류 기준
Launch FoxCode in Project Profile mode from Codex via the foxcode MCP server (`launchBrowser`). One tool call, no Python.
Test FoxCode distribution when asked to verify install/update paths, plugin packaging, marketplace contents, npm pack output, Claude Code plugin delivery, Codex plugin/config delivery, OpenCode package delivery, release readiness, or user-machine installation behavior.
Launch FoxCode in User Profile mode from Codex. Guides extension loading via about:debugging, opens connection page, verifies connectivity.
Quality-test the user-facing FoxCode skills (`foxcode-run-project-profile`, `foxcode-run-user-profile`) by spawning fresh subagents per probe so context cannot leak. Judges triggering accuracy, end-state correctness, robustness on negative prompts, and adherence to the SKILL.md flow. Use when asked to QA, audit, benchmark, regression-check, or smoke-test FoxCode skills, or to validate that a SKILL.md edit did not break the run flow.
Launch FoxCode in User Profile mode. Guides user to load extension via about:debugging, opens connection page, verifies connectivity.
Analyze historical Codex and Claude Code sessions for real FoxCode usage. Use when evaluating how effectively agents use FoxCode, evalInBrowser, launch skills, or browser automation across past sessions.
| name | foxcode-run-project-profile |
| description | Launch FoxCode in Project Profile mode via the foxcode MCP server (`launchBrowser` tool). One tool call, no Python. |
Launch isolated Firefox with the FoxCode extension. Talk to the user in their language. Be concise — minimal output, no explanations unless something fails.
The Firefox lifecycle is owned by the MCP channel: when the IDE session ends or the channel is killed, the launched Firefox closes with it.
Call MCP tool launchBrowser (no arguments are required; defaults work). Do NOT call status first — launchBrowser is idempotent: with a browser already connected it returns instantly without spawning anything, and parallel sessions in the same folder never start a second Firefox.
The tool reply is JSON. Interpret status:
connected → "Ready."already-connected → "Ready."already-running → "Ready." (a managed Firefox is already alive on the current port).timeout → relay the JSON reply unchanged; suggest the user reload the extension and re-run the skill.error → relay reason; common causes are missing Firefox binary or no free WebSocket port.The reply also carries a nested server object with channel telemetry (port, projectDir, connectedClients, serverVersion, …) — use it for diagnostics instead of a separate status call.
That is the whole flow — one tool call, no Python, no ${CLAUDE_SKILL_DIR}/scripts/*, no PID files to manage from the agent side.