Agent skill

Take Over Resume

by mtarcure in mtarcure/claude-vibe-squad

A skill your agent uses when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent…

MITAuto-check passedAgent Workflows

Install Take Over Resume

skills CLI
$ npx skills add mtarcure/claude-vibe-squad --skill take-over-resume -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install mtarcure/claude-vibe-squad take-over-resume --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/mtarcure/claude-vibe-squad.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.agents/skills/take-over-resume .claude/skills/take-over-resume && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
take-over-resume
GitHub stars
165
Token cost
~1.5k tokens
SKILL.md length
866 words
Files
1
Skills in repo
17
Repo updated
First seen
Licence
MIT

At a glance

A skill your agent uses when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent…

  • Works in 4 steps: Stop at a coherent point. Suspend… → Record the resume anchor — the commit… → State what is safe to touch, so… → …
  • Resuming work in a repository after a human
  • SKILL.md covers When to use, Pausing cleanly, Resuming and Memory: what maps, and what…, plus 2 more sections
  • Calls git

What it does

Take Over Resume is an agent skill from mtarcure/claude-vibe-squad. Use when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent, and rebuild the plan and verification baseline from current contents.

Its SKILL.md is about 1.5k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Agent Workflows. The repository describes itself as: Multi-model AI orchestration where behaviour is Markdown, not code. One coordinator routes scoped task packets to 71 role-based specialists across 5 model families (Codex /… The licence is MIT.

When your agent uses it

  • Resuming work in a repository after a human
  • Another process may have edited the tree—diff from the recorded anchor
  • Inspect untracked files
  • Treat changes as intent

Example prompts

  • “/take-over-resume”

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. Stop at a coherent point. Suspend between steps, not mid-write. A tree caught half way through a
  2. Record the resume anchor — the commit the work was built on, the tree involved, and the step that
  3. State what is safe to touch, so intervention does not collide with in-flight state.
  4. Never remove a worktree with work still in flight. Removal kills the running work. Re-read

What it can do on your machine

Read from SKILL.md and the folder at commit 7bd69f8. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • git

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md. Its commands use git, which can reach the network depending on how they are called.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Take Over Resume loads about 1.5k tokens when it runs. Until then it costs about 66 tokens; SKILL.md has 866 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~66
When it runs · the whole SKILL.md, loaded when a task matches
~1.5k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from mtarcure/claude-vibe-squad at commit 7bd69f8, republished under its MIT licence (© mtarcure). 866 words, ~1,490 tokens.

Download SKILL.mdSave it as .claude/skills/take-over-resume/SKILL.md (or your agent's skills folder).
name
take-over-resume
description
Use when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent, and rebuild the plan and verification baseline from current contents.
audience
specialist

Take-Over Resume

Resume work on a tree that a human may have changed while you were not looking. The failure mode is narrow and expensive: work resumes against a remembered state, the operator's manual fix is silently reverted or duplicated, and the conflict surfaces much later as a mysterious regression.

The controlling assumption is that the tree is the truth and your memory of it is a hypothesis.

When to use

  • Resuming a task that was paused for manual intervention.
  • Returning to a worktree after an operator hand-fix.
  • Any resume where time has passed and the tree was reachable by someone else.
  • A task that failed, was repaired by hand, and is being restarted.

Pausing cleanly

When work is being suspended for someone to intervene:

  1. Stop at a coherent point. Suspend between steps, not mid-write. A tree caught half way through a multi-file edit is one nobody can safely reason about.
  2. Record the resume anchor — the commit the work was built on, the tree involved, and the step that was about to run. This anchor is what makes the resume diff meaningful; without it, the diff has no baseline and the whole procedure degrades to guessing.
  3. State what is safe to touch, so intervention does not collide with in-flight state.
  4. Never remove a worktree with work still in flight. Removal kills the running work. Re-read in-flight status immediately before any cleanup, not from a status read earlier in the session.

Resuming

  1. Diff against the anchor before reading anything else. List the changed files, then read the actual diff. This is the first action on resume — not a check performed after planning, because a plan built on the remembered tree is already wrong.

    git diff <anchor> does not show untracked files, and a new file is the most common human edit. A file the human created is invisible to the diff alone, so the procedure would miss precisely the change that triggered it. Enumerate untracked paths separately and read them in full:

    git diff --stat <anchor>            # tracked changes
    git status --porcelain              # '??' lines are untracked and absent from the diff above

    Read every ?? path's contents, not just its name. Treat a .gitignored path as intentional scratch unless it is obviously a deliverable.

  2. Read the changes as intent. A human edit is a message: it says the previous approach was wrong, incomplete, or heading somewhere unwanted. Work out what the edit is telling you before deciding how to proceed.

  3. Reconcile the plan against reality. Steps the human already completed are done — do not redo them. Steps whose premise the edit invalidated need rework, not resumption. Say which is which.

  4. Do not revert a manual change to restore your plan. If a human edit conflicts with the plan, the plan yields, or the conflict is surfaced for a decision. Silently reverting an operator's fix is the central failure this procedure exists to prevent, and it is indistinguishable from a bug when it surfaces later.

  5. Re-run verification from the current tree. Prior results describe a tree that no longer exists. Establish a fresh baseline before attributing any failure to your own work — a failure that predates your changes is not yours to fix, and the only way to tell is to measure.

  6. Carry the change summary into the resumed work as explicit context: what changed, what it implies, and how the plan was adjusted.

Show full SKILL.md (315 more words)Show less

Memory: what maps, and what does not

The source of this procedure re-indexed each changed file into a knowledge graph as a file-snapshot node.

That has no honest equivalent here, and none is invented. chrono-vault records canonical markdown notes — attempt, finding, learning — and is not a file-content index. There is no per-file snapshot upsert, and using record to stuff file contents into note bodies would be a misuse that pollutes recall for every future query. The repository itself, through git, already is the file index; the diff against the anchor is how it is queried.

What is worth recording is the lesson, not the contents:

the anchor commit, files changed, inferred intent, and how the plan was adjusted. The exact record call shape, sequence, and fields are owned by the task packet's injected memory contract — see wirework-reflect; do not copy a record(...) example or add fields such as source_task, which the server binds.

Best-effort only — a memory error is logged in one line and never blocks the resume.

Failure modes

  • Resuming from memory — continuing without diffing, and reverting the operator's fix.
  • Missing anchor — no recorded commit at pause, so the resume diff has no baseline.
  • Redoing completed steps — treating the plan as authoritative over the tree.
  • Stale verification — trusting results from before the manual edits, and attributing a pre-existing failure to your own change.
  • Snapshot-stuffing memory — pushing file contents into notes because the source pattern indexed files and something felt owed.

Acceptance

  • The resume began with a diff against a recorded anchor, and the diff was read rather than just listed.
  • Manual changes were interpreted as intent, and no manual change was reverted without surfacing it.
  • The plan was reconciled against the tree: completed steps dropped, invalidated steps reworked.
  • Verification was re-run from the current tree before any failure was attributed.
  • No file contents were pushed into memory; only the transferable lesson was recorded, best-effort.

© mtarcure, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

Just SKILL.md in .agents/skills/take-over-resume of mtarcure/claude-vibe-squad.

Open the folder on GitHubat commit 7bd69f8

Compare with similar skills

Take Over Resume next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Take Over Resume compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Take Over Resume this skillmtarcure/claude-vibe-squad165—~1.5kAutomated safety check: PassMIT
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
Hook Development for Claude Code Pluginsanthropics/claude-plugins-official38k10 repos~4.1kAutomated safety check: NotesApache-2.0
Using Superpowersfarm-fe/farm5.6k35 repos~1.4kAutomated safety check: PassMIT
Executing Plans Inlineobra/superpowers297k2 repos~5.1kAutomated safety check: PassMIT
Skill CreatorAzure/azqr79689 repos~8.2kAutomated safety check: PassApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • Hook Development for Claude Code Plugins

    anthropics/claude-plugins-official

    Official

    Explains how to write Claude Code plugin hooks, both prompt-based checks and bash commands, for events such as PreToolUse, Stop and SessionStart.

    38k GitHub starsUsed in 10 repos~4.1k tokens
    Agent WorkflowsAuto-check: notes
  • Using Superpowers

    farm-fe/farm

    A skill your agent uses when starting any conversation - establishes how to find and use skills, requiring Skill tool invocation before ANY response including clarifying questions

    5.6k GitHub starsUsed in 35 repos~1.4k tokens
    Agent WorkflowsAuto-check passed
  • Executing Plans Inline

    obra/superpowers

    Has the agent carry out an implementation plan itself, task by task in the current session, keeping a ledger, proving each step with a test and ending with one whole-branch review.

    297k GitHub starsUsed in 2 repos~5.1k tokens
    Agent WorkflowsAuto-check passed
  • Skill Creator

    Azure/azqr

    Official

    Create new skills, modify and improve existing skills, and measure skill performance.

    796 GitHub starsUsed in 89 repos~8.2k tokens
    Agent WorkflowsAuto-check passed
  • Claude Code Agent Development

    anthropics/claude-plugins-official

    Official

    Explains how to write agents for Claude Code plugins: the markdown file with YAML frontmatter, trigger descriptions, model and color settings, and system prompt design.

    38k GitHub starsUsed in 7 repos~2.8k tokens
    Agent WorkflowsAuto-check passed

More from mtarcure/claude-vibe-squad

All 17 skills in this repo
  • Systematic Attacking

    mtarcure/claude-vibe-squad

    A skill your agent uses for ALL authorized offensive-security / bug-bounty work — the single method to find, chain, prove, dedup, and package the highest-value (High/Critical) findings across every…

    165 GitHub stars~3.6k tokensUpdated 19 days ago
    Auto-check passed
  • Blind Rediscovery

    mtarcure/claude-vibe-squad

    Operational checklist + helper for blind-rediscovery fan-out work.

    165 GitHub stars~1.6k tokensUpdated 19 days ago
    Auto-check passed
  • Chain Construct Smart Contract

    mtarcure/claude-vibe-squad

    A skill your agent uses when you have a confirmed on-chain vulnerability hypothesis and must demonstrate it with a passing proof-of-concept — author an attacker contract or crafted instruction…

    165 GitHub stars~1.5k tokensUpdated 19 days ago
    Auto-check passed
  • Compact Now

    mtarcure/claude-vibe-squad

    Operator-triggered proactive compaction — Chrono externalizes load-bearing state (active decisions, open tasks, next action) to a snapshot + a durable Vault learning note before invoking Claude…

    165 GitHub stars~1.6k tokensUpdated 19 days ago
    Auto-check passed
  • Agent Prompt Engineering

    mtarcure/claude-vibe-squad

    A skill your agent uses when building or revising the system prompt for a product agent and you need an eval-backed boundary, tool-use, grounding, and output contract.

    165 GitHub stars~872 tokensUpdated 19 days ago
    Auto-check: warnings
  • Defi Invariant Check

    mtarcure/claude-vibe-squad

    A skill your agent uses when the audit target is a DeFi protocol — AMM, lending market, yield vault, stablecoin, or perps — and you must author the economic properties generic campaigns miss, such…

    165 GitHub stars~2.5k tokensUpdated 19 days ago
    Auto-check passed

Categories

Questions about Take Over Resume

What does Take Over Resume do?

A skill your agent uses when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent…. Take Over Resume is an agent skill from mtarcure/claude-vibe-squad. Use when resuming work in a repository after a human or another process may have edited the tree—diff from the recorded anchor, inspect untracked files, treat changes as intent, and rebuild the plan and verification baseline from current contents.

When should I use Take Over Resume?

Take Over Resume fits situations like: resuming work in a repository after a human; another process may have edited the tree—diff from the recorded anchor; inspect untracked files; treat changes as intent.

How do I install Take Over Resume in Claude Code?

Run `npx skills add mtarcure/claude-vibe-squad --skill take-over-resume -a claude-code`. Or copy the skill folder (.agents/skills/take-over-resume in mtarcure/claude-vibe-squad) into .claude/skills/take-over-resume in your project. Claude Code loads it when a task matches its description.

How do I install Take Over Resume in Codex?

Run `npx skills add mtarcure/claude-vibe-squad --skill take-over-resume -a codex`. Or copy the skill folder (.agents/skills/take-over-resume in mtarcure/claude-vibe-squad) into .agents/skills/take-over-resume in your project. Codex loads it when a task matches its description.

Can I use Take Over Resume in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add mtarcure/claude-vibe-squad --skill take-over-resume -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/take-over-resume, .gemini/skills/take-over-resume, .github/skills/take-over-resume and .opencode/skills/take-over-resume in your project.

What does Take Over Resume need to run?

Going by SKILL.md and its folder, Take Over Resume needs the command-line tools its instructions call (git).

Does Take Over Resume access the network?

SKILL.md contains no URLs. Its commands use git, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Take Over Resume safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does Take Over Resume use?

Take Over Resume is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Take Over Resume use?

About 1.5k tokens (SKILL.md is roughly 6k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Take Over Resume?

Skills that share tags, products or a category with Take Over Resume: MCP Server Builder (anthropics/skills, 180k stars), Hook Development for Claude Code Plugins (anthropics/claude-plugins-official, 38k stars), Using Superpowers (farm-fe/farm, 5.6k stars) and Executing Plans Inline (obra/superpowers, 297k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Take Over Resume?

mtarcure (a GitHub user) maintains it in mtarcure/claude-vibe-squad, which has 165 GitHub stars. The repository holds 17 skills in this directory. The repository was last updated on September 21, 2026.

Source: mtarcure/claude-vibe-squad on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.