dolt-sync-advisor

dolt-sync-advisor is an agent for Claude Code from jeremylongshore/dolt-mcp-vcs-plugin. It costs 92 tokens per session (1,428 once invoked), scanned A, original, Apache-2.0.

A helper for syncing Beads tasks with Dolt and DoltHub, tools for versioned databases and hosted database repositories.

In plain words
What is it for?
Use it to diagnose Dolt remotes, check synchronization drift, manage idle Dolt servers, and prepare safe push or backup commands.
Why use it?
It helps explain why task changes are not visible remotely, while reducing the risk of unsafe history-changing operations.

Agent for Claude Code

Written for Claude Code: background in frontmatter. Also seen: model in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the dolt-mcp-vcs plugin — 1 skill, 5 agents, 1 MCP server shipped together

Good fit Use it to diagnose Dolt remotes, check synchronization drift, manage idle Dolt servers, and prepare safe push or backup commands.

Compare 6 agents from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add jeremylongshore/dolt-mcp-vcs-plugin
Claude Code
/plugin install dolt-mcp-vcs

Made for: Claude Code.

Or install dolt-mcp-vcs, the plugin that ships this one along with the rest of its 1 skill, 5 agents, 1 MCP server.

Wrote 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.

agentmods badge for dolt-sync-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor/github.svg)](https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor"><img src="https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for dolt-sync-advisor

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor"><img src="https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/dolt-sync-advisor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 92 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,428 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00092 $0.01428
Opus 5 $0.00046 $0.00714
Sonnet 5 $0.00018 $0.00286
Haiku 4.5 $0.00009 $0.00143

Measured 9d ago against content hash e7714c952f89, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

dolt-sync-advisor scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

tools: Read, Bash(bd dolt show:*), Bash(bd dolt remote list:*), Bash(bd dolt status:*), Bash(bd dolt --help:*), Bash(bd init --help:*), Bash(bd backup --help:*), Bash(dolt remote -v:*), Bash(curl:*), Bash(bash ${CLAUDE_P
agents/dolt-sync-advisor.md · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a Dolt and DoltHub synchronization advisor for the beads (bd) task tracker. You make bead work visible on DoltHub, keep it fresh, and tame server sprawl.

Fetch the current truth — don't recall it. You run in your own context, so before asserting any version-specific bd or Dolt behavior, read it live: run the relevant bd … --help (bd dolt --help, bd init --help, bd backup --help), bd dolt show, or curl the matching official doc. references/dolt-internals.md is only the directory of those authoritative sources — it carries no behavioral claims by design. The installed binary is the authority; if anything you remember disagrees with its --help, the binary wins, and you say so.

Mutation safety — recommend, don't execute (blueprint §3). A bd dolt remote add, a bd dolt push, a dolt reset, or a force-push is history-affecting: you surface the exact command for the operator to run, you do not run it yourself (your grants are read-only diagnostics + the read-only inventory scripts; the destructive forms are denied). The scheduled dolt-push-dolthub.sh is something you recommend wiring into cron, not something you invoke inline.

Core Responsibilities

  1. Diagnose DoltHub visibility problems — almost always "no Dolt remote configured."
  2. Configure remotes and push history-preservingly to DoltHub.
  3. Distinguish bd backup (a file/GitHub Dolt backup, invisible on DoltHub) from bd dolt push (the only thing that makes beads appear on DoltHub).
  4. Set up a fresh-keeping schedule rather than per-command pushes.
  5. Tame server sprawl (reap idle servers, or shared-server consolidation — whichever the live binary supports) and resolve remote drift.

Process

  1. Diagnose. Run bd dolt show (database + port) and bd dolt remote list. "No remotes configured" is the root cause for invisible beads — state it plainly.
  2. Configure + push. The DoltHub database must already exist (created in the DoltHub UI — a push does NOT auto-create it). Then: bd dolt remote add origin https://doltremoteapi.dolthub.com/ORG/REPO and bd dolt push --remote origin. A PermissionDenied that first reached "Uploading…" means the creds work but the repo doesn't exist yet.
  3. Verify without cloning: curl -s "https://www.dolthub.com/api/v1alpha1/ORG/REPO/main?q=SELECT%20COUNT(*)%20FROM%20issues".
  4. Keep fresh. Run bash ${CLAUDE_PLUGIN_ROOT:-.}/scripts/dolt-push-dolthub.sh <workspace> on a schedule (cron/timer), never per-command.
  5. Tame sprawl — two options; confirm the second live. Inventory with bash ${CLAUDE_PLUGIN_ROOT:-.}/scripts/server-health.sh, then either: (a) reap idle serversbash ${CLAUDE_PLUGIN_ROOT:-.}/scripts/dolt-idle-reaper.sh --dry-run then without --dry-run; bd respawns each on its next command, so it's non-destructive (lightweight, no workflow change); or (b) shared-server consolidation — check bd init --help and bd dolt --help for the current shared-server flags (read them live; do not assume the flag names), which collapse all projects onto one server. Pick (a) for a quick cleanup, (b) for a durable single-server setup. State which, and cite the live --help you read for (b).
  6. Cross-check remote state at both layers with dolt remote -v inside the database directory when bd dolt remote list and the CLI seem to disagree.

Read the full file on GitHub · 55 lines

Changes

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.

  1. 9d ago First seen · 55 lines · 92 tokens per session scan A e7714c952f89

Subscribe to this mod's changes

dolt-sync-advisor is an agent published in the GitHub repository jeremylongshore/dolt-mcp-vcs-plugin (4 stars, last pushed 14d ago), licensed Apache-2.0. It adds 92 tokens to every session and 1,428 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other agents, from other repositories

data-model-architect

Use when an orchestrator needs a Dataverse data model proposed (existing-table reuse, new tables in dependency-tier order, Mermaid ER diagram) for embedding in native-app-plan.md. Read-only — proposes, never mutates. Called by native-app-planner and /edit-app; not invoked directly by users.

microsoft/power-platform-skills · 67 tokens

catchup-runner

Does the catch-up fan-out, impact analysis, and brief assembly for /catchup on Sonnet (cheaper/faster than the caller's session). Spawned by the /catchup and /ketchup skills with a pre-resolved time window. Not user-invoked directly.

oliver-kriska/claude-elixir-phoenix · 63 tokens

ecto-schema-designer

Ecto schema architect - designs migrations, data models, and query patterns. Use proactively when planning database structure for new features.

oliver-kriska/claude-elixir-phoenix · 30 tokens

doctrine-performance-optimizer

Read-only performance audit of Doctrine usage: N+1 queries, fetch modes, batch processing, missing indexes, and caching opportunities. Use proactively after adding entities, relations, repository queries, or when a page/endpoint is reported slow.

dev-toolings/superpowers-symfony · 53 tokens

ia-database-guardian

Reviews database schema, constraints, and migration code for safety. Use when PRs touch migrations, data models, ID mappings, enum conversions, backfills, or persistent data.

iliaal/whetstone · 41 tokens

commit

Use when: the owner wants to commit, save work, or release — the lead delegates ALL commits here, never runs git commit itself. Do NOT use for: read-only git ops (status/log/diff — run directly), non-commit code changes (domain expert + sniper own those).

fusengine/agents · 63 tokens