mcp-sync-verify
Verify the dotfiles MCP sync pipeline is healthy after editing master/overlay/override configs or sync code.
Skill by stevencarpenter
Chalk Labs
Need help deploying mcp-sync-verify?
Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.
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/stevencarpenter-mcp-sync-verify
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: data, writing, agent-building
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
- Runs as
- Python package
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/mcp-sync-verify
What's inside
- Skill name
mcp-sync-verify- Description
- Verify the dotfiles MCP sync pipeline is healthy after editing master/overlay/override configs or sync code. USE THIS SKILL whenever the user edits anything under `home/.config/mcp/` (mcp-master.json, machine/work.json, machine/personal.json, machine/lab.json, overrides/*.json, templates), edits anything under `mcp_sync/` (sync.py, cli.py, templates/*.base.json|.toml, tests), or asks any of "sync MCP configs", "verify MCP", "did the MCP sync break", "did mcp-master change anything", "what changed in opencode/cursor/claude.json", "preview the MCP fan-out", "dry run mcp_sync", "I edited mcp/machine/*.json: does it still apply cleanly", "is codex/cursor/junie/lmstudio still in sync". Bias toward triggering after edits to the MCP source-of-truth files even if the user does not explicitly ask: this skill never writes to deployed paths, so the cost of an unnecessary trigger is one tmpdir.
- License
- unknown
- Instructions
- 123 lines in SKILL.md · view on GitHub
Before installing
- Ships executable scripts
- Instructions read files in your home folder (~/.ssh, ~/.aws…)
Agent Skills spec issues
- files: referenced but missing: scripts/hooks-sync.sh
- body: contains an absolute path from the author's machine
Files (3)
- SKILL.md
- dry_run_diff.sh · scripts/
- print_target_paths.py · scripts/
The license isn't open source, so the instructions aren't shown here. Read SKILL.md on GitHub
More from stevencarpenter/dotfiles
- 0.583score
dotfiles-secret-authoring
stevencarpenter
Apply authoring-time secret judgment in this public dotfiles repo.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
sandbox-preflight
stevencarpenter
Diagnose an observed sandbox or filesystem permission failure in this repository.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
adopt-config
stevencarpenter
Adopt an unmanaged tool configuration into this dotfiles-manager repository as a checkout link.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
kaneo-issue
stevencarpenter
File, update, or close tasks in the self-hosted Kaneo workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
claude-cost
stevencarpenter
Estimate AI coding-agent spend from local Claude Code (Anthropic) and Codex (OpenAI) session logs, broken down by provider and model with cache-aware pricing.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
blind-review
stevencarpenter
Experimental paired code review with comments and docstrings removed from one pass.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
uv-tool-loop
stevencarpenter
Run the repository's mcp_sync lint and test commands, diagnose environment or collection failures, and keep tests isolated from deployed user configuration.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
monitoring-hippo
stevencarpenter
Use when user asks if hippo is working, running, healthy, or needs debugging.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
ponytail-gain
stevencarpenter
Show ponytail's measured impact as a compact scoreboard: less code, less cost, more speed, from the benchmark medians.
SkillBFreshness: B★ 1Claude Code +9 - 0.542score
ponytail-debt
stevencarpenter
Harvest every `ponytail:` comment in the codebase into a debt ledger, so the deliberate shortcuts and deferrals ponytail leaves behind get tracked instead of…
SkillBFreshness: B★ 1Claude Code +9 - 0.541score
journaling
stevencarpenter
Use when agent-journal is configured and material work should be captured in the user's journal.
SkillBFreshness: B★ 1Claude Code +9 - 0.539score
domain-model
stevencarpenter
Stress-test a plan against the project's domain language and documented decisions, resolve material ambiguities, and capture agreed terminology or…
SkillBFreshness: B★ 1Claude Code +9
Signals
- Stars
- 1
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Oct 17, 2026 (13 days ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- License unknown
- Repository
- github.com/stevencarpenter/dotfiles
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from stevencarpenter
- 0.583score
dotfiles-secret-authoring
stevencarpenter
Apply authoring-time secret judgment in this public dotfiles repo.
SkillAFreshness: A★ 1Claude Code +9 - 0.582score
sandbox-preflight
stevencarpenter
Diagnose an observed sandbox or filesystem permission failure in this repository.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
kaneo-issue
stevencarpenter
File, update, or close tasks in the self-hosted Kaneo workspace.
SkillAFreshness: A★ 1Claude Code +9 - 0.580score
adopt-config
stevencarpenter
Adopt an unmanaged tool configuration into this dotfiles-manager repository as a checkout link.
SkillAFreshness: A★ 1Claude Code +9 - 0.547score
claude-cost
stevencarpenter
Estimate AI coding-agent spend from local Claude Code (Anthropic) and Codex (OpenAI) session logs, broken down by provider and model with cache-aware pricing.
SkillBFreshness: B★ 1Claude Code +9 - 0.544score
blind-review
stevencarpenter
Experimental paired code review with comments and docstrings removed from one pass.
SkillBFreshness: B★ 1Claude Code +9
Done for you
Rather not set it up yourself?
Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.
See how we build AI agents →Read the case studies
Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.
- launches shipped
- 50+
- launches shipped
- media placements
- 500+
- media placements
- founders on every account
- 2
- founders on every account
Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block
Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.
Get mcp-sync-verify running in your business
Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.
Cite this page
mcp-sync-verify skill. Agent Mart. https://agentmart.dev/skills/stevencarpenter-mcp-sync-verify (last updated 2026-10-24)