メニュー
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.
Codex または Claude でインストール この Prompt をコピーして Codex、Claude、または他のアシスタントに貼り付けると、Skill ページを確認してインストールできます。
SOC 職業分類に基づく
Launch FoxCode in Project Profile mode from Codex via the foxcode MCP server (`launchBrowser`). One tool call, no Python.
Launch FoxCode in Project Profile mode via the foxcode MCP server (`launchBrowser` tool). 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.
| name | foxcode-usage-analysis |
| description | 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. |
Analyze past Codex and Claude Code sessions to measure real FoxCode usage.
documents/requirements.md and documents/design.md for current FoxCode context.python3 .agents/skills/foxcode-usage-analysis/scripts/analyze_foxcode_usage.py
actual_sessions: sessions with real status, evalInBrowser, or launch helper calls.mention_files: noisy upper bound; includes sessions where FoxCode only appears in available tools/skills.eval_sessions: sessions that actually used browser automation.reliable_flags: sessions with concrete errors (No connection, Timeout (, invalid selector, missing host permission).recent_actual examples in the script output before drawing conclusions.foxcode appears in the system prompt or tool catalog.launch_firefox + status counts and low evalInBrowser.evalInBrowser calls after a successful connection, with few reliable flags.text= and :has-text(...) inside evalInBrowser arguments indicate Playwright-style selector confusion; FoxCode DOM helpers expect CSS selectors.Missing host permission often means the agent navigated to a tab or URL where the extension cannot inject. Prefer api.eval(fetch(...)) from an allowed page for same-origin API checks.Return a concise report:
Scope: history locations, file counts, date range if visible.
Codex: actual sessions, eval sessions, call counts, reliable flags, main bottleneck.
Claude Code: actual sessions, eval sessions, call counts, reliable flags, main bottleneck.
Patterns: recurring inefficiencies and evidence.
Recommendations: concrete changes to FoxCode skills/docs.
If the script cannot read one IDE's history, report that path as blocked and continue with the other IDE.