groom

groom is a command for Claude Code from jwynia/context-networks. It costs 0 tokens per session (1,082 once invoked), scanned A, original, MIT.

A command for turning a project's task lists and notes into a clear, actionable backlog, which is the ordered list of work still to do.

In plain words
What is it for?
Finding tasks across planning and project files, filtering them by readiness, blockers, age, domain, or complexity, and creating a sprint plan.
Why use it?
It separates ready, vague, blocked, stale, completed, and obsolete tasks so the team can focus on work that is actually prepared.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

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.

agentmods
npx agentmods add commands/jwynia/context-networks/groom
Clone the repo
git clone --depth 1 https://github.com/jwynia/context-networks

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 groom

README.md
[![agentmods](https://agentmods.dev/badge/commands/jwynia/context-networks/groom.svg)](https://agentmods.dev/commands/jwynia/context-networks/groom)
Your own site
<a href="https://agentmods.dev/commands/jwynia/context-networks/groom"><img src="https://agentmods.dev/badge/commands/jwynia/context-networks/groom.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,082 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00000 $0.01082
Opus 5 $0.00000 $0.00541
Sonnet 5 $0.00000 $0.00216
Haiku 4.5 $0.00000 $0.00108

Measured 6d ago against content hash 3a3e73c27e0f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

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 6d 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/commands/groom.md · 162 lines

How it starts

The opening of the file, as written. The whole thing — 162 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Task Grooming Specialist

You are a Task Grooming Specialist responsible for transforming the context network's task list into a clear, actionable backlog.

Grooming Request

$ARGUMENTS

Command Options

Parse $ARGUMENTS for options:

  • --ready-only - Only show tasks that are ready for implementation
  • --blocked - Focus on identifying and unblocking blocked tasks
  • --stale [days] - Re-groom tasks older than specified days
  • --domain [name] - Groom tasks for specific domain only
  • --complexity [trivial|small|medium|large] - Filter by complexity level
  • --generate-sprint - Create a sprint plan from groomed tasks

Grooming Process

Phase 1: Task Inventory & Classification

Scan all task sources:

  • /planning/sprint-*.md
  • /planning/backlog.md
  • /tasks/**/*.md
  • /decisions/**/*.md (for follow-up actions)
  • /domains/**/todo.md
  • Files with "TODO:", "NEXT:", "PLANNED:" markers

Classify each task as:

  • A: Claimed Complete - Marked done but needs follow-up
  • B: Ready to Execute - Clear criteria, no blockers
  • C: Needs Grooming - Vague requirements or missing context
  • D: Blocked - Waiting on dependencies or decisions
  • E: Obsolete - No longer relevant or duplicate

Phase 2: Reality Check

For each task, assess:

  • Still Needed? Check against current project state
  • Prerequisites Met? Identify missing dependencies
  • Implementation Clear? Flag ambiguities
  • Success Criteria Defined? Note what's missing
  • Complexity Estimate: Trivial/Small/Medium/Large/Unknown

Phase 3: Task Enhancement

Transform vague tasks into actionable items with:

  • Specific, measurable title
  • Clear context and rationale
  • Input/output specifications
  • Acceptance criteria checklist
  • Implementation notes
  • Identified dependencies
  • Effort estimate
  • Related documentation links

Phase 4: Dependency Analysis

Create dependency map showing:

  • Tasks ready now (no dependencies)
  • Tasks ready after current work
  • Blocked chains with specific blockers
  • Decision points needed

Read the full file on GitHub · 162 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. 6d ago First seen · 162 lines · 0 tokens per session scan A 3a3e73c27e0f

Subscribe to this mod's changes

groom is a command published in the GitHub repository jwynia/context-networks (24 stars, last pushed 1y ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,082 tokens. 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.

ai