bead-review

bead-review is a skill for Claude Code from punt-labs/punt-kit. It costs 32 tokens per session (2,154 once invoked), scanned A, original, MIT.

A backlog-audit process that reviews every open bead, meaning a tracked unit of work, for clarity, validity, and priority.

In plain words
What is it for?
Use it to clean up and prioritize all open beads in one repository, grouping the results by theme for later batch implementation.
Why use it?
It removes work items that are no longer real and rewrites the rest so the backlog accurately describes the work. It reviews the whole repository backlog without asking for separate approval on each item.

Skill for Claude Code

Written for Claude Code: ${CLAUDE_PLUGIN_ROOT} variable. Also seen: reads .claude/ paths; mentions subagents.

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 punt-dev plugin — 2 skills, 13 commands shipped together

Good fit Use it to clean up and prioritize all open beads in one repository, grouping the results by theme for later batch implementation.

Compare 6 skills 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 punt-labs/punt-kit
Claude Code
/plugin install punt-dev

Made for: Claude Code.

Or install punt-dev, the plugin that ships this one along with the rest of its 2 skills, 13 commands.

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 bead-review

README.md
[![agentmods](https://agentmods.dev/badge/skills/punt-labs/punt-kit/bead-review/github.svg)](https://agentmods.dev/skills/punt-labs/punt-kit/bead-review)
Your own site
<a href="https://agentmods.dev/skills/punt-labs/punt-kit/bead-review"><img src="https://agentmods.dev/badge/skills/punt-labs/punt-kit/bead-review/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 bead-review

Your own site · 80×15
<a href="https://agentmods.dev/skills/punt-labs/punt-kit/bead-review"><img src="https://agentmods.dev/badge/skills/punt-labs/punt-kit/bead-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,154 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 $0.00032 $0.02154
Opus 5 $0.00016 $0.01077
Sonnet 5 $0.00006 $0.00431
Haiku 4.5 $0.00003 $0.00215

Measured 10d ago against content hash ff2f5e18c59a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

bead-review 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 10d 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.

plugin/skills/bead-review/SKILL.md · 221 lines

How it starts

The opening of the file, as written. The whole thing — 221 lines — stays where its author put it; the contents beside it link to each section on GitHub.

bead-review — Full Backlog Audit

Review 100% of a repo's open beads, one at a time, in this same session, against the per-bead rubric in references/per-bead-rubric.md. This is a backlog cleanup pass, not implementation work — nothing gets fixed in code here, only the beads describing the work get made accurate, clear, and correctly prioritized (or closed if the work they describe is no longer real).

No per-bead confirmation. The rubric makes the call on each bead autonomously. This skill's job is to enumerate, apply the rubric, reconcile, and produce one final report — not to relay N individual questions to the user.

Usage

args (optional): a repo directory to scope to (defaults to the current working directory). Beads are stored in a shared org-wide database but scoped per repo via .beads/metadata.json's prefix. To audit multiple repos, invoke this skill once per repo; it does not fan out across repos on its own.

Skill(bead-review)                      # audits the current repo
Skill(bead-review, args="../vox")       # audits a sibling repo

Set REPO once at the start of the run: args if given, otherwise the current directory. Never cd — every bd command below takes -C "$REPO" instead, so the skill works regardless of what tools are allow-listed for the invoking command.

Step 1: Confirm scope

cat "$REPO/.beads/metadata.json"   # confirm the prefix, sanity-check this is the right db

State the repo and prefix you're about to audit in one line before starting — this is not a confirmation question, just an announcement, so the run is legible if it's being watched.

Step 2: Enumerate every open bead

"Open" means any non-closed status, not just bd ready's narrower no-blockers view — blocked and deferred beads still need clarity/validity review even if they can't be worked yet. Do not add --all here — that flag means "include closed issues too," the opposite of what this step wants; the explicit --status list is the complete filter on its own:

Read the full file on GitHub · 221 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 10d ago First seen · 221 lines · 32 tokens per session scan A ff2f5e18c59a

Subscribe to this mod's changes

bead-review is a skill published in the GitHub repository punt-labs/punt-kit (1 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 2,154 once invoked, about $0.0002 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.

Related

Other skills, from other repositories

traction-eos

Implement the Entrepreneurial Operating System (EOS) to align vision and execution across a company. Use when the user mentions "EOS", "Entrepreneurial Operating System", "V/TO", "quarterly rocks", "Level 10 meetings", "accountability chart", "IDS process", "my company feels chaotic", "we keep having the same…

wondelai/skills · 147 tokens

promote-idea

Converts an album idea from IDEAS.md into an actual album project in one step. Use when the user says "promote [idea title]", "turn idea into album", or "start working on [idea]".

bitwize-music-studio/claude-ai-music-skills · 50 tokens

customer-onboarding-and-implementation

Takes a new customer from signature to working — setting a definition of live that both sides agreed before the contract was signed, planning and staffing the implementation, running data migration and integration realistically, training the people who will actually use it, and handing over to the ongoing…

cbrock84/headcount · 94 tokens

vendor-management

Selects, contracts, and manages suppliers and vendors — requirements, evaluation, negotiation support, onboarding, performance management, and exit. Use this to choose a vendor, run a selection process, structure a service agreement's operational terms, manage an underperforming supplier, plan an exit or migration, or…

cbrock84/headcount · 69 tokens

recap-doc

Post-development recap document generator. Use when: AI/Codex has implemented a feature and the user needs a guided walkthrough of what changed and why, with blind-spot detection and anticipated questions. Not for: Q&A follow-up (use /recap-ask), technical share-out for teammates (use /tech-brief), or generic code…

sd0xdev/sd0x-harness · 114 tokens

runbook

Generate and update feature release runbooks from existing docs and codebase. Use when: creating operational runbook, release handbook, deployment checklist, pre-release preparation. Not for: incident response (v2), code review (use codex-code-review), architecture design (use architecture).

sd0xdev/sd0x-harness · 59 tokens