Skip to content

tzachbon/srulik-toolkit / plugins/srulik-toolkit/skills/takeover

takeover

Verified

Take over work another agent, session, or harness started. Use when the user switches agents, hands off a conversation, says "take over" or "continue where you left off", or is unhappy with earlier work. Rebuilds the problem, Definition of Done, verified progress, scope creep, and new intent, then continues or waits for confirmation. For a catch-up without continuing, use `recap`.

FileKindSize
SKILL.mdskill md3.3 KB
references/sources.mdmarkdown1.3 KB

references/sources.md

View on GitHub
# Where earlier sessions live

Read this when the handoff points to another session or gives no transcript.
These locations were observed on one Linux host; check that a path exists
before relying on it.

| Host | Find the earlier session | Watch for |
| --- | --- | --- |
| Claude Code | JSONL files in `projects/<cwd-slug>/` under the Claude configuration root (`CLAUDE_CONFIG_DIR`, else `.claude` in the home directory). The slug is the working directory with `/` and `.` replaced by `-`. | Context summaries replace older turns; say which part you saw only as a summary. Subagent transcripts sit in a `subagents/` folder. |
| Codex | `sessions/YYYY/MM/DD/rollout-*.jsonl` under the Codex home (`CODEX_HOME`, else `.codex` in the home directory). User text is in `response_item` entries with role `user`. | Harness and `AGENTS.md` text also arrive as user-role items; skip them. Match the session by its `cwd` in `session_meta`. |
| T3 Code | `t3_thread_search` or `t3_thread_list` to find the thread, then `t3_thread_read` with `view: "activity"`, paging with `afterPosition`. | A provider switch hands over a note such as "Selected 0 intact items". The original thread still holds the history. |

On any other host, including Cursor, this mapping is untested: ask the user to
paste or export the earlier conversation, and work from the repository until
they do.
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 471kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 322kUpdated Claude CodeCodexVerifiedInstall