backlog-item-groomer

backlog-item-groomer is an agent for Claude Code from Jamie-BitFlight/claude_skills. It costs 84 tokens per session (5,695 once invoked), scanned A, original, MIT.

An agent that prepares a backlog item for planning by gathering its context, related resources, dependencies, and missing information. It also checks the item's acceptance criteria against its observable behaviour.

In plain words
What is it for?
Use it to research a backlog item, identify related skills and previous work, map dependencies, determine the relevant artifact type, and produce a standard groomed-item template.
Why use it?
It reduces unclear or underspecified backlog work before implementation begins, while flagging gaps instead of filling them with guesses.

Agent for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: model in frontmatter; reads .claude/ paths; mentions subagents.

Part of the dh plugin — 53 skills, 28 agents shipped together

Good fit Use it to research a backlog item, identify related skills and previous work, map dependencies, determine the relevant artifact type, and produce a standard groomed-item template.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/jamie-bitflight/claude_skills/backlog-item-groomer
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/Jamie-BitFlight/claude_skills

Made for: Claude Code.

Or install dh, the plugin that ships this one along with the rest of its 53 skills, 28 agents.

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-item-groomer

README.md
[![agentmods](https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/backlog-item-groomer/github.svg)](https://agentmods.dev/agents/jamie-bitflight/claude_skills/backlog-item-groomer)
Your own site
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/backlog-item-groomer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/backlog-item-groomer/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 backlog-item-groomer

Your own site · 80×15
<a href="https://agentmods.dev/agents/jamie-bitflight/claude_skills/backlog-item-groomer"><img src="https://agentmods.dev/badge/agents/jamie-bitflight/claude_skills/backlog-item-groomer.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 5,695 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 $0.05695
Opus 5 $0.00042 $0.02848
Sonnet 5 $0.00017 $0.01139
Haiku 4.5 $0.00008 $0.00570

Measured 7d ago against content hash a6b6582d62c7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

backlog-item-groomer 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 7d 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.

plugins/development-harness/agents/backlog-item-groomer.md · 556 lines

How it starts

The opening of the file, as written. The whole thing — 556 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Backlog Item Groomer Agent

Receives a backlog item and returns groomed content in the standard template format. The orchestrator stores the output through backlog_groom. Return the content — do not write it anywhere yourself.

Scope Boundary

You are an autonomous research agent for problem clarification and resource discovery.

You are NOT a solution designer.

You verify facts against primary sources, estimate effort, map dependencies, identify the primary artifact type, identify the artifact's behavioral boundary, and discover existing resources in the codebase.

You do NOT produce architecture specs, task decompositions, implementation plans, code design, or detailed solution design. Those happen in the SAM planning phase downstream.

Your output makes items ready for planning by ensuring the problem is well understood, the target behavior is clear, the available resources are mapped, and the acceptance criteria evaluate the item using the correct domain semantics.

When information is missing, surface it as a blocker or question. Do not fill gaps with assumptions.

Core Principle

A groomed backlog item must describe the externally observable behavior that proves the work is done.

"Observable" does not mean "surface-level artifact exists."

"Observable" means "the artifact fulfills its purpose at its real boundary."

Examples:

  • For a bug fix, the observable boundary is the previously failing behavior.
  • For a feature, the observable boundary is the user-visible or agent-visible workflow.
  • For an MCP tool, the observable boundary is the tool call contract.
  • For an agent, the observable boundary is the agent's behavior when assigned a task.
  • For a skill, the observable boundary is the behavior of an agent using that skill.

Skills are behavioral automation instructions for agents. Do not treat skills as static documents or non-functional documentation. A skill is done when an agent using it behaves correctly on representative tasks.

Input

  • item_ref: the backlog item reference (#N, title substring, beads nanoid, or URL)
  • RT-ICA summary (optional): pre-computed RT-ICA assessment from the orchestrator or the rtica-assessor agent — when present in the dispatch, use it directly and skip Step 0's own pass; focus discovery on filling MISSING conditions and validating DERIVABLE ones instead.

Read the full file on GitHub · 556 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. 7d ago Changed a6b6582d62c7
  2. 9d ago First seen · 556 lines · 84 tokens per session scan A ded72991d976

Subscribe to this mod's changes

backlog-item-groomer is an agent published in the GitHub repository Jamie-BitFlight/claude_skills (66 stars, last pushed today), licensed MIT. It adds 84 tokens to every session and 5,695 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 2026-09-03.

Related

Other agents, from other repositories

project-implementer

Implementation specialist - executes tasks from plans with TDD methodology, writes tests, and validates acceptance criteria. Use for executing phased implementation plans generated by attune:plan.

athola/claude-night-market · 38 tokens

scrum-master

Scrum Master agent (Bob) — generates story files from Epic Manifest rows and the delivery file.

LuisFelipeMoro/Harness-devkit · 24 tokens

onboard-guide

Onboarding assistant that provides ongoing personalized guidance after initial /onboard. Use for questions about conventions, architecture, patterns, or "where do I put this?" — answers are tailored to the engineer's background.

smicolon/ai-kit · 46 tokens

jira-analyst

Read full Jira ticket context (description, comments, attachments, links, media) and produce structured analysis suitable for posting back as a Jira comment. Read-only via the jira-as CLI wrapper. Routed by mk:jira-analyst skill. NOT for complexity scoring (jira-evaluator); NOT for story-point estimation…

ngocsangyem/MeowKit · 72 tokens

pm-advisor

You are pm-advisor — great-pm's external-perspective product advisor. You are NOT a process reviewer. You are the seasoned operator the founder pulls aside and says: "Be honest — what do you actually think of this?".

VandanaAjayDubey111/great-pm · 123 tokens

goals-onboarding

Use this agent to set up the OKR/goals system for a new company or project. Guides the user through defining annual objectives, key results, team quarterly OKRs, initiatives, tasks, support functions, and org chart. Generates YAML files following the workspace goals schema. Examples: Context: User wants to set up…

41fred/ace-level1 · 206 tokens