gur-workflow

gur-workflow is a skill for Claude Code, Codex from Giancarlos/guardrails. It costs 11 tokens per session (2,060 once invoked), scanned A, original, MIT.

A guide to managing work items with gur, a command-line task manager designed for AI-agent workflows.

In plain words
What is it for?
Use it to create and organize tasks, bugs, features, and larger epics, then move them from open to in progress, closed, and archived.
Why use it?
It provides a consistent task lifecycle, priorities, types, labels, assignees, and subtasks so work does not become difficult to track.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to create and organize tasks, bugs, features, and larger epics, then move them from open to in progress, closed, and archived.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/giancarlos/guardrails/gur-workflow
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 Giancarlos/guardrails --skill gur-workflow
Clone the repo
git clone --depth 1 https://github.com/Giancarlos/guardrails

Made for: Claude Code, Codex.

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 gur-workflow

README.md
[![agentmods](https://agentmods.dev/badge/skills/giancarlos/guardrails/gur-workflow/github.svg)](https://agentmods.dev/skills/giancarlos/guardrails/gur-workflow)
Your own site
<a href="https://agentmods.dev/skills/giancarlos/guardrails/gur-workflow"><img src="https://agentmods.dev/badge/skills/giancarlos/guardrails/gur-workflow/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 gur-workflow

Your own site · 80×15
<a href="https://agentmods.dev/skills/giancarlos/guardrails/gur-workflow"><img src="https://agentmods.dev/badge/skills/giancarlos/guardrails/gur-workflow.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 11 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,060 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 $0.00011 $0.02060
Opus 5 $0.00005 $0.01030
Sonnet 5 $0.00002 $0.00412
Haiku 4.5 $0.00001 $0.00206

Measured 9d ago against content hash 4fd688b90a3a, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gur-workflow 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 9d 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.

skills/gur-workflow/SKILL.md · 381 lines

How it starts

The opening of the file, as written. The whole thing — 381 lines — stays where its author put it; the contents beside it link to each section on GitHub.

gur Workflow Skill

This skill teaches effective use of gur, a task management CLI designed for AI agent workflows.

Core Concepts

Task Lifecycle

open -> in_progress -> closed -> archived
  • open: Task is ready to be worked on
  • in_progress: Actively being worked on
  • closed: Completed with a close reason
  • archived: Historical record, can be compacted to save context

Priority Levels

  • P0 (Critical): Drop everything, fix now
  • P1 (High): Important, address soon
  • P2 (Medium): Normal priority (default)
  • P3 (Low): Nice to have
  • P4 (Lowest): Backlog

Task Types

  • task: General work item (default)
  • bug: Defect to fix
  • feature: New functionality
  • epic: Large initiative containing subtasks

Command Patterns

Creating Tasks

Basic task:

gur create "Implement user authentication"

With full context:

gur create "Fix login timeout bug" \
  --type bug \
  --priority 1 \
  --label security \
  --label auth \
  --assignee agent

From template:

gur create "Add payment processing" --template feature-checklist

Working With Subtasks

Create parent epic:

gur create "User management system" --type epic
# Returns: gur-a1b2c3d4

Add subtasks:

gur create "Design user schema" --parent gur-a1b2c3d4
gur create "Implement CRUD endpoints" --parent gur-a1b2c3d4
gur create "Add validation" --parent gur-a1b2c3d4

Subtasks get hierarchical IDs: gur-a1b2c3d4.1, gur-a1b2c3d4.2, etc.

Managing Dependencies

Block a task until another completes:

# "auth" blocks "dashboard" (dashboard can't close until auth is done)
gur dep add gur-auth123 gur-dash456

Check what's blocking:

gur show gur-dash456  # Shows "Blocked by: gur-auth123"

Find unblocked tasks ready for work:

gur ready

Quality Gates

Gates enforce checks before task closure.

Create a gate:

gur gate create "Unit tests pass" --type test --command "go test ./..."
gur gate create "Code review approved" --type review
gur gate create "Security scan clean" --type approval --priority 0

Read the full file on GitHub · 381 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. 9d ago First seen · 381 lines · 11 tokens per session scan A 4fd688b90a3a

Subscribe to this mod's changes

gur-workflow is a skill published in the GitHub repository Giancarlos/guardrails (24 stars, last pushed 4mo ago), licensed MIT. It adds 11 tokens to every session and 2,060 once invoked, about $0.0001 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 2026-08-30.