debug-onlisted

Use this skill when the user wants to debug an init, evo, or security-audit session, or wants to attribute iEvo token costs in a usage dashboard — trigger words "turn on debug", "verbose mode", "log everything", "trace level", "debug logging", "cost monitoring", "OTel cost attribution", "OTEL_RESOURCE_ATTRIBUTES", "tag iEvo usage by team or project". Enables verbose / trace-level logging across the iEvo pipeline — captures full prompts, full sub-agent returns, every Task tool dispatch, every gh/git/network call, environment dump — and documents how to label Claude Code's OTel metrics so iEvo token spend can be sliced separately from ordinary coding usage in an OTel-backed dashboard. Output goes to `.ievo/log/debug/<session-id>/` for post-mortem analysis. Activates by writing `.ievo/debug.flag` (project-level setting).
ievo-ai/skills · ★ 0 · Code & Development · score 72

Install: claude install-skill ievo-ai/skills

# Debug On — enable verbose session logging Activates trace-level logging for all subsequent iEvo skill invocations in this session and future sessions, until `/ievo:debug-off` is invoked. Flag is project-local (lives in `.ievo/debug.flag`), so teammates working in the same repo see it via git too. > **Claude Code v2.1.181+ alternative.** For a quick one-off check, `/config verbose=true` ([release notes](https://github.com/anthropics/claude-code/releases/tag/v2.1.181)) toggles Claude Code's own verbose output inline — zero-install, no `.ievo/` write. It is not a substitute for this skill: the setting doesn't persist as a git-shareable project flag, doesn't write to `.ievo/log/debug/`, and covers Claude Code only — this skill also captures full sub-agent prompts/returns and works across Codex/Cursor/other agentskills.io platforms. See `/ievo:debug-off` for the matching `/config verbose=false` note. ## When to use - User says "turn on debug", "verbose mode", "log everything", "trace level" - User reports a bug in init/evo/security-audit and wants reproducible logs - User wants to share a session for issue filing on ievo-ai/skills - User wants to understand iEvo's internal decision-making - **Documentation only — nothing is enabled:** user asks how to attribute, label, or slice iEvo token spend ("cost monitoring", "tag iEvo usage by team or project", `OTEL_RESOURCE_ATTRIBUTES`). Answer from § "Cost monitoring (Claude Code v2.1.161+)" and stop — see Step 0. ## Steps ### 0.