Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/lacolaco/claude-plugins/takeovernpx skills add lacolaco/claude-plugins --skill takeovergit clone --depth 1 https://github.com/lacolaco/claude-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lacolaco/claude-plugins/takeover)<a href="https://agentmods.dev/skills/lacolaco/claude-plugins/takeover"><img src="https://agentmods.dev/badge/skills/lacolaco/claude-plugins/takeover.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00129 | $0.03509 |
| Opus 5 | $0.00064 | $0.01754 |
| Sonnet 5 | $0.00026 | $0.00702 |
| Haiku 4.5 | $0.00013 | $0.00351 |
Grade A, and why
takeover scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Take over a job seat that a previous holder has handed off (or vacated). This is job succession with accountability transfer: you are not the predecessor and you do not inherit their mind. You are the next person on the seat. From this moment onward you are accountable for what happens in it — including for any of the predecessor's failures that surface during your tenure.
Your starting posture: the predecessor underperformed. A successor is needed only because the predecessor could not bring the work to a finished state within their tenure. That is a structural fact, not a personal judgment: if the work were complete, no one would be taking over. The seat came to you because the previous holder was, by definition, inadequate to close it on their watch. Approach their handoff report with this in mind — there is necessarily something they missed, got wrong, could not solve, or did not realize was a problem. Your audit job is not "did they get this right?" but "where did they go wrong, and what did they not see?" Assume problems exist until you have personally verified otherwise. A clean-looking handoff is a signal to look harder, not to relax.
You must work differently from the predecessor — and you owe the seat its credibility back. Repeating the predecessor's approach will produce the predecessor's outcome: you will hit the same walls, miss the same things, and be relieved the same way. The seat has lost credibility because the predecessor could not deliver, and restoring that credibility is part of the job, not a side concern. As you read their report and audit their claims, ask not only "is this correct?" but also "what about their way of working failed, and what should I do differently?" Look for the process gaps that let their failures slip through — premature certainty, skipped verification, narrow framing, anchoring on a wrong model — and adopt explicit safeguards against repeating them in your own work. You are not just continuing the task; you are showing the seat can be held to a higher standard than the predecessor managed.
The predecessor's handoff package is yours to audit, not to adopt unexamined. Treat their Knowledge block as a colleague's status report at a handoff meeting: take it seriously, but no inherited claim becomes your own until you have verified it. Anything you build on an unverified inheritance is your own risk, and your own accountability if it bites.
The workspace's handover directory has already been resolved for you (walked up from $PWD to the nearest .handover/, or fallen back to $HOME/.handover):
<base> = !`handover-dir`
Handover documents live at <base>/<holder>.md, named after the current holder. The seat itself is identified by the document's frontmatter (project + role), not by the filename. Use the absolute <base> above verbatim for every list/read/rename below — never construct the path from cwd yourself.
Step 1: Choose the seat to take over
/takeover <holder>(argument given) — take over the seat currently held by<holder>. No prompt./takeover(no argument) — list<base>/*.mdand let the user choose:- If the directory is empty: there is no seat to take. Tell the user and continue as a new subject (you have no seat yet; one is minted only if you later run
/handover). - Otherwise present the seats with
AskUserQuestion. Each option:-
label =
<holder> — <project>/<role>when the document has v4 frontmatter, else just<holder>(legacy v3.x or older). -
description = the document's frontmatter
descriptionfield plus its last-modified time. Read only the frontmatter, not the body. A document has frontmatter iff its first line is exactly---; otherwise treat it as pre-v3 and show(no description). Extractproject,role, anddescriptionwith:awk 'NR==1 && $0!="---"{exit} /^---$/{c++; if(c==2) exit; next} c==1 && /^(project|role|description):[[:space:]]*/{key=$1; sub(/^[^:]*:[[:space:]]*/, "", $0); print key" "$0}' <base>/<file>.md
-
- If the directory is empty: there is no seat to take. Tell the user and continue as a new subject (you have no seat yet; one is minted only if you later run
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 138 lines · 129 tokens per session scan A 1e898015ddd8
takeover is a skill published in the GitHub repository lacolaco/claude-plugins (5 stars, last pushed 8d ago), licensed MIT. It adds 129 tokens to every session and 3,509 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
wayfinder
Plan a huge chunk of work (more than one agent session can hold) as a shared map of decision tickets on your issue tracker, and resolve them one at a time until the way to the destination is clear.
sap-transport-overview
System-wide inventory of open transport requests — every visible modifiable request, who owns it, how big it is, and supported risk signals such as empty/local requests, explicit locks, and confirmed manifest overlaps. Headers-only and cheap; NO source diffs. Use when asked "what transports are open in the system"…
timeline-creator
Create HTML timelines and project roadmaps with Gantt charts, milestones, phase groupings, and progress indicators. Use when users request timelines, roadmaps, Gantt charts, project schedules, or milestone visualizations.
okx-task-watch
监听任务进展 / 帮我盯着任务 / 任务有动静告诉我 / 历史消息 / 未读消息 / 未决策 / 待决策 / 继续监听 / task watch / user watch / monitor task progress / catch me up on tasks / outstanding decisions — OKX A2A user-session task-notification monitor: live long-poll via okx-a2a user watch (also drains backlog of past/missed/unread events on entry) plus…
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).
bootstrap-prd
Set up PRD-driven development infrastructure for a new project, including directory structure, templates, and roadmap.