[agents](https://carteblanche.com/index.md?kind=agent) / [business](https://carteblanche.com/index.md?category=business) # backlog-grooming what it does Use when the user needs to groom, refine, or clean up a product backlog. Triggers on: 'groom backlog', 'backlog refinement', 'backlog grooming', 'clean up backlog', 'refine stories', 'sprint refinement', 'backlog management'. tools it asks for Reads files · Edits files · Uses the web Both automated reviewers said it asks for more access than its job needs. by VoltAgent · version 1 · license MIT We imported this agent from its author’s repository. Is this yours? [Claim this listing](https://carteblanche.com/claim/backlog-grooming) Verified · Before and after: 2 models · 1 try per case · [View source](https://github.com/VoltAgent/awesome-claude-code-subagents/blob/ed74d115b7fb7026a22a4f816a8e3250f425e3b4/categories/08-business-product/backlog-grooming.md) · [Install from your agent](https://carteblanche.com/connect.md) · [Download .zip](https://carteblanche.com/skills/backlog-grooming/download) ## Compare the answers Answers from Claude Sonnet 5.5 and GPT-6.1 Sol · try 1 of 1 Same request, same model, once with the agent’s instructions as its system prompt and once without. Neither could use a tool. Read both and judge for yourself. [Compare the answers](https://carteblanche.com/skills/backlog-grooming/compare) ## The models 2 models Claude Sonnet 5.5 made by Anthropic claude-sonnet-5-5 · revision not reported by the provider 1 try per case · tested 7 Nov 2026 GPT-6.1 Sol made by OpenAI gpt-6.1-sol · revision not reported by the provider 1 try per case · tested 7 Nov 2026 ## The tasks written by Carte Blanche **example-1** “Can you help me groom our backlog? Here are the items: 1) 'Improve search' (no acceptance criteria, been open 14 months), 2) 'As a user I want to reset my password via SMS' (est. 8 pts), 3) 'Fix login bug' (no repro steps), 4) 'Dark mode' (duplicate of 'Theme support'), 5) 'Migrate DB to Postgres 16' (epic-sized, no breakdown). Tell me what to close, merge, split, or send back for more detail, and rewrite the ones worth keeping as proper stories.” **example-2** “We have sprint refinement tomorrow and I need to refine these three stories: 'As an admin I can export reports', 'As a customer I get notified about order status', and 'Make checkout faster'. For each, please suggest clear acceptance criteria in Given/When/Then format, flag open questions for the team, note any that are too big for one sprint and how to split them, and propose a rough priority order using value vs effort.” ## Install Download the .zip and unzip it. Put `backlog-grooming.md` here: Claude Code · `~/.claude/agents/` · Every project. For one project only, use .claude/agents/ inside it. It gives the agent the tools it asks for, and no others. Cursor · `~/.cursor/agents/` · Cursor also reads the Claude Code folder above. It has no tools field, so it gives every agent every tool, whatever this one asks for. Codex · Codex’s custom agents are TOML files, not Markdown, so this agent doesn’t install there. Keep its license file beside it, as `backlog-grooming.LICENSE`: a name that doesn’t end in .md, since every .md file there is read as an agent. Then start a new session and ask for it by name. Folders checked 6 November 2026. Or [install from your agent](https://carteblanche.com/connect.md): ask it to install `backlog-grooming` from Carte Blanche. ## Badge for your README Carte Blanche: Verified Paste this into the agent’s README. It links to this page, and shows how the listing stands whenever it’s loaded. ``` [![Carte Blanche](https://carteblanche.com/badge/backlog-grooming.svg)](https://carteblanche.com/skills/backlog-grooming) ``` ## About this test - **tested**: 7 Nov 2026 - **version tested**: v1 - **cases**: 2 - **tries per case**: 1 try per case - **run without the agent**: yes - **cases written by**: Carte Blanche - **size**: 3037 characters What this shows, and what it doesn’t How 2 models answered these 2 requests, with and without the agent. It says nothing about other models, and it doesn’t limit what your own agent can do. The answers were written without tools: the agent’s instructions were the system prompt, and it read no file and ran nothing. [How we test](https://carteblanche.com/how-it-works.md)