backlog-groom

backlog-groom is a skill for Claude Code from flurdy/agent-skills. It costs 60 tokens per session (4,727 once invoked), scanned A, original, MIT.

A read-only quality review of every open Beads task, looking for incomplete descriptions, incorrect labels or priorities, outdated notes, duplicates, and work that should be split into smaller tasks.

In plain words
What is it for?
Use it to audit open tasks and produce proposed corrections. It reports changes for approval instead of editing the backlog automatically.
Why use it?
It makes the backlog easier to understand and reduces wasted effort caused by vague, duplicated, outdated, or poorly structured tasks.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: model in frontmatter; names the AskUserQuestion tool.

Good fit Use it to audit open tasks and produce proposed corrections. It reports changes for approval instead of editing the backlog automatically.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/flurdy/agent-skills/backlog-groom
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.

Any agent
npx skills add flurdy/agent-skills --skill backlog-groom
Clone the repo
git clone --depth 1 https://github.com/flurdy/agent-skills

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 backlog-groom

README.md
[![agentmods](https://agentmods.dev/badge/skills/flurdy/agent-skills/backlog-groom.svg)](https://agentmods.dev/skills/flurdy/agent-skills/backlog-groom)
Your own site
<a href="https://agentmods.dev/skills/flurdy/agent-skills/backlog-groom"><img src="https://agentmods.dev/badge/skills/flurdy/agent-skills/backlog-groom.svg" alt="Measured on agentmods" height="20"></a>
Per session 60 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,727 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. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 6
    Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.
    Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.
How audits are shown
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 $0.00060 $0.04727
Opus 5 $0.00030 $0.02364
Sonnet 5 $0.00012 $0.00945
Haiku 4.5 $0.00006 $0.00473

Measured today against content hash e629d08649df, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

backlog-groom 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 today.

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.

skills/backlog-groom/SKILL.md · 232 lines

How it starts

The opening of the file, as written. The whole thing — 232 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog Groom — Per-Bead Quality Audit

Walk the open backlog and ask, for each bead: is this any good? Flag hygiene, priority, lifecycle, structure, and duplicate problems, propose a concrete fix for each, and only mutate on explicit approval.

This is the hygiene counterpart to the intake/reconciliation skills — it is the only one that systematically reads every open bead and improves its quality.

Relationship to other tools

  • /triage is forward intake: prompt/Jira → new bead(s), with dup-check and splitting at creation time. The groomer does not create beads from prompts and does not re-implement splitting — when a bead obviously needs splitting, it hands the bead to /triage.
    • /triage <bead-id> (refine mode) is the depth counterpart to this sweep: it investigates one existing bead against the code, then deepens, corrects, or splits it. Hand a bead there whenever grooming it needs real investigation rather than a one-shot edit — see the "be fast" rule below.
  • /tracking-sweep is cross-system drift (Jira ↔ beads ↔ PRs), read-only. The groomer does not re-implement cross-system linking — when a bead lacks a Jira/Trello link, it flags it and points at /tracking-sweep (or /trello-beads).
  • tracking-auditor (agent) is per-branch: does THIS diff match its ticket? Unrelated.
  • /backlog-groom (this skill) is per-bead quality of the backlog itself: descriptions, labels, priority, lifecycle, structure, duplicates.

If a finding belongs to one of those tools, delegate — don't duplicate its logic.

Usage

/backlog-groom                 # Read-only sweep of open beads → proposal report. Changes nothing.
/backlog-groom apply           # After showing the report, batch-apply the SAFE proposals on approval;
                               #   destructive ones still confirm one at a time.
/backlog-groom all             # Widen scope to open + ready + blocked (default is open only).
/backlog-groom labels          # Just the DB-wide label-normalisation pass (fast).
/backlog-groom lint            # Opt in to template-conformance checks (AC / Steps / Success Criteria).
/backlog-groom <bead-id> …     # Groom only the named beads.

Read the full file on GitHub · 232 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. today Changed · -81 tokens per session e629d08649df
  2. 8d ago First seen · 232 lines · 141 tokens per session scan A dd64224e2032

Subscribe to this mod's changes

backlog-groom is a skill published in the GitHub repository flurdy/agent-skills (9 stars, last pushed yesterday), licensed MIT. It adds 60 tokens to every session and 4,727 once invoked, about $0.0003 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

recipe-create-meet-space

Create a Google Meet meeting space and share the join link.

googleworkspace/cli · 18 tokens

workthreads

SpecStory Workthreads - a weekly work-thread rollup across a team's repos from SpecStory coding histories (any agent - Claude Code, Codex, Cursor, Gemini, and more). It groups the window's sessions into threads of work per project and labels each new / open / recently closed, so a lead sees what shipped, what is still…

specstoryai/getspecstory · 126 tokens

atmos-config

Atmos root configuration: atmos.yaml discovery, precedence, deep merging, basepath, imports, minimal bootstrap, and routing to narrower Atmos skills.

cloudposse/atmos · 31 tokens

story-readiness

Validate that a story file is implementation-ready. Checks for embedded GDD requirements, ADR references, engine notes, clear acceptance criteria, and no open design questions. Produces READY / NEEDS WORK / BLOCKED verdict with specific gaps. Use when user says 'is this story ready', 'can I start on this story', 'is…

Donchitos/Claude-Code-Game-Studios · 77 tokens

autotask-creator

Rules for automation CRUD from the group-chat commander. The commander does not call mutation tools and does not edit cloud/autotasks files directly. It emits one or more top-level ... containers in its final text; the bus parses and applies them after the turn.

Orkas-AI/Orkas · 5 tokens

monorepo-management

Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.

wshobson/agents · 54 tokens