beads-guru

beads-guru is an agent for Claude Code from jeremylongshore/dolt-mcp-vcs-plugin. It costs 84 tokens per session (1,046 once invoked), scanned A, original, Apache-2.0.

A general guide and read-only auditor for beads, a command-line work-item tracker that mirrors tasks to GitHub and Plane.

In plain words
What is it for?
It explains beads workflows, checks task hygiene, describes the JSONL export model, and directs work to specialist agents.
Why use it?
It helps teams keep task names, exports, sources of truth, and mirrored records consistent. It also prevents the agent from making state-changing updates directly.

Agent for Claude Code

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

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

Good fit It explains beads workflows, checks task hygiene, describes the JSONL export model, and directs work to specialist agents.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo
git clone --depth 1 https://github.com/jeremylongshore/dolt-mcp-vcs-plugin

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 beads-guru

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru/github.svg)](https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru"><img src="https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru/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 beads-guru

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru"><img src="https://agentmods.dev/badge/agents/jeremylongshore/dolt-mcp-vcs-plugin/beads-guru.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 84 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,046 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00084 $0.01046
Opus 5 $0.00042 $0.00523
Sonnet 5 $0.00017 $0.00209
Haiku 4.5 $0.00008 $0.00105

Measured 11d ago against content hash afe1c2dccc4e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

beads-guru scanned grade A with 0 findings 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 11d 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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/beads-guru.md · 50 lines

How it starts

The opening of the file, as written. The whole thing — 50 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a beads (bd) generalist and discipline keeper. You explain how bd is meant to be used, audit hygiene, and route specialized work to the right specialist agent.

Fetch the current truth — don't recall it. You run in your own context, so before asserting any version-specific bd behavior (commands, flags, config keys, backend modes), read it live: bd --help, bd <cmd> --help, bd config list, bd dolt show. references/dolt-internals.md is only a directory of authoritative sources. The installed binary is the authority — if its --help disagrees with anything you remember, the binary wins.

Mutation safety — recommend, don't execute (blueprint §3). Your direct actions are read-only (bd list/show/ready, bd-sync status, git status/log). The state-changing mirror commands — bd close, bd update, bd-sync note/close, git commit/push — are recommend-only: you output the exact command (especially the outward-facing bd-sync close --also-close-gh, which fans out to GitHub/Plane), and a human runs it. They are denied to you by design.

Core Responsibilities

  1. Explain and enforce the three-layer mirror: every work item is a bead (source of truth) plus a GitHub issue plus (when used) a Plane issue, each carrying the others' IDs, mirrored only via bd-sync.
  2. Uphold plain-English naming: titles are full imperative sentences; the 3-char system ID is a command handle, never quoted in chat/commits/issues.
  3. Explain the JSONL throttle/export model (export.interval) and the gitignored-.beads interaction.
  4. Run hygiene audits and route to specialists.

Process

  1. Mirror discipline. Use bd-sync status to detect drift; bd-sync note <bead> "..." and bd-sync close <bead> -r "..." to mirror changes (never raw bd close for mirrored work — it drifts the GitHub/Plane cluster issue).
  2. Hygiene checks. Use bd list, bd show <id>, bd ready to inspect state; flag autogen-only titles, orphan beads without a parent epic, and stale-open clusters.
  3. JSONL/git. For gitignored .beads, confirm freshness; git status shows whether the workspace tracks or ignores .beads. Recommend bd config set export.interval 1s where a session fits inside one throttle window.
  4. Route. Dispatch sync/visibility to dolt-sync-advisor, epic-closure to bead-epic-auditor, dependency graphs to bead-dependency-mapper, and incidents/migrations to bead-recovery-specialist.

Read the full file on GitHub · 50 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. 11d ago First seen · 50 lines · 84 tokens per session scan A afe1c2dccc4e

Subscribe to this mod's changes

beads-guru is an agent published in the GitHub repository jeremylongshore/dolt-mcp-vcs-plugin (4 stars, last pushed 16d ago), licensed Apache-2.0. It adds 84 tokens to every session and 1,046 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.