agent-sync
Synchronize a shared repository after switching between Codex and Claude.
Skill by shabanakhtar
Chalk Labs
Need help deploying agent-sync?
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/shabanakhtar-agent-sync
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: 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
Network hosts it talks to 1
codeload.github.com· found in install command
Files it touches
~/.claude/skills/agent-sync
What's inside
- Skill name
agent-sync- Description
- Synchronize a shared repository after switching between Codex and Claude. Invoke manually as `/agent-sync check` after returning from the other AI or `/agent-sync end` before handing work off.
- License
- MIT
- Instructions
- 36 lines in SKILL.md · view on GitHub
Agent Skills spec issues
- name: "agent-sync" does not match folder "claude"
Files (1)
- SKILL.md
SKILL.md (first lines)
# Agent Sync Use the project files as the source of truth. Do not rely on stale chat context. ## Modes ### `/agent-sync check` Use after an agent switch and before repository-changing work when another AI may have worked since the last sync. 1. Read `AGENTS.md`, `CLAUDE.md` when present, `AGENT_HANDOFF.md`, and the relevant part of `PROJECT_PLAN.md`. 2. Inspect `git status`, recent commits, and diffs. Read files named under **Active Work** or open **Review Ledger** rows. 3. Review the other agent's proposed change or request. Record a concise result in its ledger row: `agree`, `needs change`, `implemented`, or `not applicable`, with the reviewed paths. 4. Update only the current agent's line in **Sync State**. Do not create artificial history entries. 5. Report the actual state succinctly. Do not implement new website work unless the user explicitly authorizes it. Do not commit, push, stage unrelated files, or erase another agent's uncommitted work during `check`. ### `/agent-sync end` Use before handing work to the other AI. 1. Run the same reconciliation checks as `check`; resolve or clearly leave open every relevant ledger row. 2. Update **Active Work**, **Next Step**, **Sync State**, and only the handoff details needed by the next agent. 3. Keep `AGENT_HANDOFF.md` compact. The proposing agent removes a resolved ledger row after the other AI's review has been consumed. Non-core resolved notes may be removed immediately; preserve user decisions, active blockers, and one-line delivery history. 4. Verify work in proportion to risk. Stage explicit owned paths only; inspect staged diff; commit and push only when the user has authorized it. Never use `git add -A` in a shared tree. 5. State what remains open and the exact next action. ## Ledger Rules - Put temporary proposals, review requests, and cross-agent questions in **Review Ledger**, not `AGENTS.md`. - The agent that created a row owns its deletion after both agents have reviewed it or it is cleanly resolved. - Move permanent, user-approved constraints to **User Decisions**. Do not delete those without user direction. - If another agent's changes are unclear, leave the row open and ask rather than guessing.
From shabanakhtar/ai-agent-skills, MIT.
More from shabanakhtar/ai-agent-skills
- 0.470score
agent-sync
shabanakhtar
Synchronize a shared repository after switching between Codex and Claude.
SkillCFreshness: CClaude Code +9 - 0.470score
my-voice
shabanakhtar
Write or rewrite text in Shaban's natural voice.
SkillCFreshness: CClaude Code +9 - 0.468score
email-draft-polish
shabanakhtar
Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and…
SkillCFreshness: CClaude Code +9 - 0.467score
project-kickoff
shabanakhtar
Use immediately when starting a new software project, setting up a repo, kicking off a project, creating a fresh codebase, or preparing Claude Code and Codex…
SkillCFreshness: CClaude Code +9 - 0.251score
codex
shabanakhtar
No description from the publisher yet.
SkillCFreshness: CClaude Code +9
Signals
- Stars
- 0
- Forks
- 0
- Open issues
- 0
- Last commit (this folder)
- Jul 11, 2026 (3 months ago)
From GitHub (fetched Oct 24, 2026).
Details
- License
- MIT
- Repository
- github.com/shabanakhtar/ai-agent-skills
- First seen
- Oct 24, 2026
- Last checked
- Oct 24, 2026
- Source
- GitHubgithub-graphql
More from shabanakhtar
- 0.470score
agent-sync
shabanakhtar
Synchronize a shared repository after switching between Codex and Claude.
SkillCFreshness: CClaude Code +9 - 0.470score
my-voice
shabanakhtar
Write or rewrite text in Shaban's natural voice.
SkillCFreshness: CClaude Code +9 - 0.468score
email-draft-polish
shabanakhtar
Draft, rewrite, or condense emails with target tone, length, and audience; use for cold outreach, replies, status updates, or escalations where clarity and…
SkillCFreshness: CClaude Code +9 - 0.467score
project-kickoff
shabanakhtar
Use immediately when starting a new software project, setting up a repo, kicking off a project, creating a fresh codebase, or preparing Claude Code and Codex…
SkillCFreshness: CClaude 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 agent-sync 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
agent-sync skill. Agent Mart. https://agentmart.dev/skills/shabanakhtar-agent-sync (last updated 2026-10-24)