beads-warden

beads-warden is an agent for Claude Code from jeremylongshore/tons-of-skills-marketplace. It costs 157 tokens per session (2,930 once invoked), scanned A, original, MIT.

An audit guide for Beads, a project execution record that stores work items and their dependencies. It checks that this record agrees with related GitHub issues and history.

In plain words
What is it for?
Use it to inspect Beads records, verify writes, find dependency cycles and orphaned items, review epic closure claims, and propose corrections for a human or coordinator to apply.
Why use it?
It catches lost updates, incorrect dependency graphs, overstated completed work, and open items whose reasoning or premise is no longer valid.

Agent for Claude Code

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

Good fit Use it to inspect Beads records, verify writes, find dependency cycles and orphaned items, review epic closure claims, and propose corrections for a human or coordinator to apply.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jeremylongshore/tons-of-skills-marketplace/beads-warden
About the project

Tons of Skills is a model-agnostic marketplace that distributes reusable skills, plugins, agents, commands, hooks, and settings for coding-agent tools. It is intended for people who want to browse, install, and manage agent extensions, with Claude Code as its verified native harness. The catalogue entries are extensions provided by or associated with this marketplace.

jeremylongshore/tons-of-skills-marketplace · 2,717 stars · on GitHub · tonsofskills.com

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/tons-of-skills-marketplace

Made for: Claude Code.

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-warden

README.md
[![agentmods](https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden/github.svg)](https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden)
Your own site
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden/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-warden

Your own site · 80×15
<a href="https://agentmods.dev/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden"><img src="https://agentmods.dev/badge/agents/jeremylongshore/tons-of-skills-marketplace/beads-warden.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 157 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,930 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 $0.00157 $0.02930
Opus 5 $0.00078 $0.01465
Sonnet 5 $0.00031 $0.00586
Haiku 4.5 $0.00016 $0.00293

Measured 13d ago against content hash 63525307fcb4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

beads-warden 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 13d 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.

.claude/agents/beads-warden.md · 246 lines

How it starts

The opening of the file, as written. The whole thing — 246 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Beads is the canonical execution state for this estate — GitHub Issues and Intent OS are projections of it, never authorities over it. That makes a wrong bead worse than a wrong comment: it is the record future sessions rebuild their understanding from after compaction. You keep that record honest.

You audit and report. You do not perform the work a bead describes, and you hold no Write or Edit tools. You may run bd read commands freely; you propose bd writes for a human or the orchestrating agent to execute.

Core responsibilities

  1. Enforce write-flush-verify — the bd rapid-write race silently drops state, so a command that printed success is not evidence the state changed.
  2. Route graph questions to their ownersbead-dependency-mapper for cycles and critical path, bead-epic-auditor for epic closure drift — then verify the record they read is trustworthy against Dolt commit history.
  3. Catch mislabeled closures — a bead whose title promises more than the closure delivered.
  4. Flag undispositioned or premise-rotted beads — open work with no recorded reasoning, and beads whose stated premise current evidence disproves.
  5. Reconcile projections — bd ↔ GitHub Issue ↔ Plane drift.

Process

Step 1 — Verify the writes actually landed

This is the failure you exist for. bd ≤1.1.x drops state changes when writes run in tight sequence (upstream mode 6). The command prints success. The state does not change. Batch loops, stop-hooks, and multi-bead scripts hit it constantly; this estate has lost notes and closures to it repeatedly.

The only safe shape is one change per command, a JSONL flush between each, then a read-back:

bd close <id> -r "<evidence>"                       # or update / defer
bd export -o .beads/issues.jsonl >/dev/null 2>&1    # load-bearing, not optional
bd show <id> | head -1 | grep -oE 'OPEN|IN_PROGRESS|BLOCKED|CLOSED|DEFERRED'

When auditing a batch someone else ran, re-read every bead they claim to have written and compare to the intent. Never accept the transcript as proof. Report any bead whose state does not match what the operator believed. Two additional traps:

Read the full file on GitHub · 246 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. 13d ago First seen · 246 lines · 157 tokens per session scan A 63525307fcb4

Subscribe to this mod's changes

beads-warden is an agent published in the GitHub repository jeremylongshore/tons-of-skills-marketplace (2,717 stars, last pushed today), licensed MIT. It adds 157 tokens to every session and 2,930 once invoked, about $0.0008 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 2026-08-30.

Related

Other agents, from other repositories