agentleFS
Sign inStart free
driangledriangle/vibeview/tasks/CLAUDE.md

vibeview / tasks

CLAUDE.md4 starsChanged 8 months agoMITView on GitHub

This project uses taskmd for task management. Tasks are markdown files with YAML frontmatter. See TASKMD_SPEC.md for the full field reference. Files follow the pattern ID-descriptive-title.md (e.g., 01h5a3mpk-add-user-auth.md). Solo workflow (default): 1. Verify all acceptance criteria are met 2. Run taskmd verify <id> if the task has verify checks 3. Update status: taskmd set <id> --status completed 4. Run taskmd validate to confirm no issues PR-review workflow (when workflow: pr-review in .taskmd.yaml): 1. Open a pull request with your changes…

The file

We split this CLAUDE.md into the rules it gives an agent

9 rules. About 0 are common, 3 are distinctive, and 6 are very specific to this project.

  • ≈0

    Common · estimate

    Many files like this have a rule of this kind.

  • ≈3

    Distinctive · estimate

    This author's own choices. Worth a look.

  • 6

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Run taskmd next or check dependencies with taskmd graph --format ascii

    line 56
  2. Very specific:

    Check off subtasks (- [x]) as you complete them

    line 58
  3. Distinctive:

    Verify all acceptance criteria are met

    line 63
  4. Very specific:

    Run taskmd verify <id> if the task has verify checks

    line 64
  5. Very specific:

    Run taskmd validate to confirm no issues

    line 66
  6. Distinctive:

    Stop -- the task completes when the PR is merged

    line 71
  7. Very specific:

    When worklogs are enabled (worklogs: true in .taskmd.yaml), record progress with:

    line 80
  8. Distinctive:

    Write entries when starting, making key decisions, hitting blockers, or finishing.

    line 87
  9. Very specific:

    Run taskmd validate before committing to check for missing fields, invalid values, duplicate IDs, circular dependencies, and broken …

    line 91

≈ “Common” is an estimate: at least 1 in 5 of the 26,980 CLAUDE.md files we read have a rule of the same kind, not the same words. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
CLAUDE.md

Working with Taskmd Tasks

This project uses taskmd for task management. Tasks are markdown files with YAML frontmatter. See TASKMD_SPEC.md for the full field reference.

Task File Format

---
id: "01h5a3mpk"
title: "Task title"
status: pending
priority: high
effort: medium
dependencies: ["002"]
tags: [feature]
created: 2026-01-15
---

# Task Title

## Objective

What this task accomplishes.

## Tasks

- [ ] Subtask 1
- [ ] Subtask 2

## Acceptance Criteria

- Criterion 1

Files follow the pattern ID-descriptive-title.md (e.g., 01h5a3mpk-add-user-auth.md).

CLI Commands

taskmd list                              # List all tasks
taskmd list --status pending --priority high  # Filter tasks
taskmd next                              # Find next available task
taskmd validate                          # Check for errors
taskmd graph --format ascii              # View dependency graph
taskmd board                             # Kanban board view
taskmd stats                             # Project statistics
taskmd set <id> --status in-progress     # Update task status
taskmd add "Task title"                  # Create a new task
taskmd verify <id>                       # Run acceptance checks

Task Workflow

Starting a Task

  1. Run taskmd next or check dependencies with taskmd graph --format ascii
  2. Update status: taskmd set <id> --status in-progress
  3. Check off subtasks (- [x]) as you complete them

Completing a Task

Solo workflow (default):

  1. Verify all acceptance criteria are met
  2. Run taskmd verify <id> if the task has verify checks
  3. Update status: taskmd set <id> --status completed
  4. Run taskmd validate to confirm no issues

PR-review workflow (when workflow: pr-review in .taskmd.yaml):

  1. Open a pull request with your changes
  2. taskmd set <id> --status in-review --add-pr <url>
  3. Stop -- the task completes when the PR is merged

Dependencies

  • A task with unmet dependencies should stay pending or blocked
  • Circular dependencies are invalid -- use taskmd validate to detect them

Worklogs

When worklogs are enabled (worklogs: true in .taskmd.yaml), record progress with:

taskmd worklog <id> --add "Started implementation. Approach: ..."
taskmd worklog <id>            # View worklog

Write entries when starting, making key decisions, hitting blockers, or finishing.

Validation

Run taskmd validate before committing to check for missing fields, invalid values, duplicate IDs, circular dependencies, and broken references.

Reference

  • Full specification: TASKMD_SPEC.md
  • CLI help: taskmd --help or taskmd <command> --help

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.

Check your setup, free