cleanup
Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers…
Skill by jesse-merhi
Install
Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.
npx agentmarket install skill/jesse-merhi-cleanup
Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.
Get the weekly diff
The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.
About
Use cases: productivity
Reviews
Write a reviewNo reviews yet. Installed it? Reviews come from verified installers only. How reviews work
Permissions
What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.
- Tools
- No tools found
- Secrets
- None asked for
- Install scripts
- None found
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/cleanup
What's inside
- Skill name
cleanup- Description
- Discover and remove local development artifacts that belong to finished or abandoned work, including worktrees, branches, stashes, processes, watchers, containers, volumes, build outputs, and simulator state. Use when asked to clean up after a task, PR, branch, worktree, or dev environment; not for source-code refactoring or remote resource deletion.
- License
- MIT
- Instructions
- 101 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- files: referenced but missing: references/artifact-discovery.md
Files (1)
- SKILL.md
SKILL.md (first lines)
# Cleanup Treat cleanup as an ownership problem, not a keyword search. Find the complete local footprint of the target work, remove what is proven disposable, preserve saved or shared state, and verify the footprint is gone. ## Scope and authority A request to clean up authorizes removal of clearly target-owned, local, disposable artifacts. It does not authorize deletion of remote branches or resources, user-authored work, credentials, shared infrastructure, or machine-wide caches. Before mutating anything, identify: - the target repository, worktree, branch or stack, and whether it is merged or explicitly abandoned - exact identity signals such as absolute paths, Git refs, project names, Compose labels, process working directories, ports, bundle IDs, and simulator or emulator names - a stable checkout or directory from which cleanup can continue if the target worktree disappears If the target is not clear, infer it from the current task, repository state, and recent commands. Ask only when multiple live targets remain plausible or a choice changes what data will be lost. ## Discover the footprint Read repository instructions and cleanup scripts before inventing commands. Inspect the tools and services the work actually used, then read [the artifact discovery guide](references/artifact-discovery.md) for the relevant categories. Build one inventory with each item classified as: - **remove**: exact target ownership and disposable state are established - **keep**: shared, active, reusable, remote, or unrelated - **decision**: ownership or data value is ambiguous Use native ownership metadata first: Git worktree records, Compose project labels, Watchman roots, process working directories, pidfiles, service manifests, and platform identifiers. A matching substring alone is not proof. Discovery is complete when every artifact category implied by the repository, task history, and running tools has been inspected and every found item is classified. Report the inventory before deletion only when it contains a decision item or the user asked for a dry run. ## Protect recoverable work Stop and request a decision before removing: - uncommitted or untracked files that may be user-authored - a branch with unique commits that is neither merged nor explicitly abandoned - a stash that cannot be tied unambiguously to the target - a volume, database, simulator, emulator, or cache that may contain reusable data or serve another checkout - infrastructure whose ownership is shared or unclear Prefer ordinary Git deletion after proving ancestry. Force-delete a local branch only after squash/rebase merge or abandonment is independently confirmed. Remote deletion remains a separate, explicit action. ## Remove in dependency order Keep the target worktree available until it has supplied the configuration and identity evidence needed for cleanup. Then: 1. Stop target-owned processes, dev servers, and task runners gracefully when possible. 2. Use each tool's scoped teardown operation for services, containers, databases, networks, volumes, watchers, and platform state. 3. Remove target-owned temporary files, logs, sockets, pidfiles, generated outputs, and non-shared caches that remain. 4. Remove the Git worktree, matching local branch, target-specific stashes, and stale worktree metadata. Run from the stable location, use exact paths or ownership selectors, and keep shared services running. Broad commands such as global container pruning, deleting every Watchman watch, generic `pkill`, shutting down every simulator, or repository-wide forced `git clean` are outside scoped cleanup. When the target is the agent's current worktree, finish all reads from it first, run removal from the stable checkout, and make worktree deletion the final filesystem mutation. Continue verification only from the stable location. ## Verify and report Repeat the discovery queries using the same exact identities. Cleanup is complete when every discovered item is either absent, deliberately retained, or awaiting an explicit user decision, and the stable checkout is healthy. Report: - what was removed - what was intentionally retained and why - anything unresolved, including the exact decision needed - whether remote branches or resources were left untouched
From jesse-merhi/skills, MIT.
More from jesse-merhi/skills
- 0.569score
just-do-it
jesse-merhi
Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-claude
jesse-merhi
Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-codex
jesse-merhi
Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
feedback-hardening
jesse-merhi
Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then…
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
grilling
jesse-merhi
Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
atlassian-cloudid-jira
jesse-merhi
Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
finding-discipline
jesse-merhi
Confirm actionable review findings, deduplicate root causes, and exclude nits, vague risks, and style notes.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
model-writing-guides
jesse-merhi
Select model-specific writing guidance for another skill, including exact coverage checks, same-family fallback, and one task-wide stale-coverage notice.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
design
jesse-merhi
Route UI design work among production visual design, interaction and motion implementation, read-only motion review, and explicit multi-variant prototyping.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
design-technical-diagrams
jesse-merhi
Create or refine architecture, lifecycle, sequence, trust-boundary, decision, threat-model, SVG, or HTML diagrams that explain system relationships.
SkillBFreshness: B★ 4Claude Code +9 - 0.562score
handoff
jesse-merhi
Transfer the current work to a fresh full agent session, placing related work beside the current session and unrelated asides separately.
SkillBFreshness: B★ 4Claude Code +9 - 0.559score
improve-codebase-architecture
jesse-merhi
Review architecture for module depth, interfaces, locality, dependencies, and testability.
SkillBFreshness: B★ 4Claude Code +9
Signals
- Stars
- 4
- Forks
- 2
- Open issues
- 0
- Last commit (this folder)
- Sep 4, 2026 (1 month ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/jesse-merhi/skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from jesse-merhi
- 0.569score
just-do-it
jesse-merhi
Take one well-defined, cohesive change from its current implementation or delivery checkpoint through exact-head code review, proof, CI, and a reviewer-ready…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
feedback-hardening
jesse-merhi
Evidence-backed user corrections or self-detected mistakes revealing reusable agent failures: delegate one systemic-fix recommendation, get approval, then…
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-claude
jesse-merhi
Ask Claude from a non-Claude harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.566score
ask-codex
jesse-merhi
Ask Codex from a non-Codex harness through a full ACP session for an independent answer or explicitly scoped implementation.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
grilling
jesse-merhi
Stress-test a plan, decision, or idea through relentless questions and explicit grill requests.
SkillBFreshness: B★ 4Claude Code +9 - 0.563score
atlassian-cloudid-jira
jesse-merhi
Query Jira, JPD, and Confluence through local Rovo Dev MCP, including site IDs, JQL, CQL, and boards.
SkillBFreshness: B★ 4Claude Code +9
Cite this page
cleanup skill. Agent Mart. https://agentmart.dev/skills/jesse-merhi-cleanup (last updated 2026-10-24)