Maxxing Tasks
Read or edit the Harness Maxxing task board (<workspace>/tasks.json) safely - add, update, move, complete or list tasks and task projects. Use when the user talks about their tasks, to-do list, kanban, what is due today, or asks to add/close a task.
mkdir -p ~/.claude/skills/maxxing-tasks && curl -fsSL 'https://raw.githubusercontent.com/makushingu/harness-maxxing/main/skills/maxxing-tasks/SKILL.md' -o ~/.claude/skills/maxxing-tasks/SKILL.md
Get the complete skill folder, including its scripts and reference files.
When to use this skill
Use Maxxing Tasks when an AI agent needs a reusable SKILL.md workflow for this job: Read or edit the Harness Maxxing task board (<workspace>/tasks.json) safely - add, update, move, complete or list tasks and task projects. Use when the user talks about their tasks, to-do list, kanban, what is due today, or asks to add/close a task.
When not to use it
Skip Maxxing Tasks when the task is outside the writing category, or when a more specific skill in this directory already covers the same workflow with clearer triggers.
How to install
Where will you use it?
mkdir -p ~/.claude/skills/maxxing-tasks && curl -fsSL 'https://raw.githubusercontent.com/makushingu/harness-maxxing/main/skills/maxxing-tasks/SKILL.md' -o ~/.claude/skills/maxxing-tasks/SKILL.md
- Claude Code personal install: place the skill and its bundled files at ~/.claude/skills/maxxing-tasks/SKILL.md. For a shared project, commit the folder at .claude/skills/maxxing-tasks/ instead.
- Current Claude Code detects SKILL.md changes in watched directories during the session. If you just created a top-level skills directory, run /reload-skills. Check that the skill is listed before testing its trigger.
- For Claude chat or Cowork in the Desktop app, manage uploaded skills in Customize > Skills; copying files into a local Claude Code folder is not a Desktop install. Other agents may use different install locations.
Full install guide for Claude, Cursor, and Codex →
Try a starter prompt
After installing the skill, paste this starter prompt into your agent to verify it triggers on a small task.
Use the Maxxing Tasks skill for this task: Use Maxxing Tasks when this documented workflow matches the task. Confirm any required inputs or files before making changes.
What supports this recommendation?
71/100 provisional content score. This measures documentation, practical detail and source signals. It is not a measured task success rate or a security certification.
- Documentation
- 77/100
- Practical detail
- 68/100
- Source evidence
- 63/100
- Source signals
- 72/100
Model compatibility evidence
- claudeuntested
No model-specific signal or recorded compatibility test was found.
- chatgptuntested
No model-specific signal or recorded compatibility test was found.
- geminiuntested
No model-specific signal or recorded compatibility test was found.
- copilotuntested
No model-specific signal or recorded compatibility test was found.
- llamauntested
No model-specific signal or recorded compatibility test was found.
- perplexityuntested
No model-specific signal or recorded compatibility test was found.
- mistraluntested
No model-specific signal or recorded compatibility test was found.
- grokuntested
No model-specific signal or recorded compatibility test was found.
Inferred compatibility is based on content signals. Check the app, its available tools and setup requirements before running a skill.
What this skill does
# Tasks (tasks.json)
The Tasks page of the UI reads `<workspace>/tasks.json` (workspace from `maxxing status`, here `{{WORKSPACE}}/tasks.json`). The server re-reads the file when it changes, so your edits show up in the UI within seconds.
## Schema ```json { "version": 1, "projects": [{"id": "p_ab12", "name": "acme", "color": "#6366f1", "workspace": "acme"}], "tasks": [{ "id": "t_9f3c2a", "title": "Write the launch post", "notes": "markdown", "status": "todo", "priority": 2, "due": "2026-05-04", "project_id": "p_ab12", "topic_path": "projects/acme/topics/blog", "labels": ["writing"], "created": 1767225600.0, "updated": 1767225600.0, "done_at": null, "order": 1000.0 }] } ``` - `status`: `todo` | `doing` | `done`. `priority`: 0 (none) … 3 (urgent). `due`: `YYYY-MM-DD` or null. - `project_id` refers to `projects[].id`. Every workspace project has its task project, linked by `"workspace": "<project folder name>"` (created by Harness, renamed with the project): to file a task under workspace project `acme`, use the id of the project whose `workspace` is `acme`. Projects without `workspace` are free projects (e.g. "Personal"); a task may also have no project. `hidden: true` = left out of the page's projects bar. Never delete a linked project. - `topic_path` optionally links a workspace topic (`projects/acme/topics/blog`); a task with a `topic_path` and no `project_id` is attached to that project's task project automatically. - `order`: float, sort order inside a column (to insert between two tasks use the mean of their orders). - Timestamps are Unix seconds (float). Set `done_at` when moving to `done`, null otherwise. - Ids: `t_` + 6 hex chars for tasks, `p_` + 4 hex for projects; must be unique.
## Safe editing (always) 1. Read the whole file; if it is not valid JSON, **stop** and tell the user (the UI refuses to overwrite a corrupt file too). 2. Change only what is needed; **keep unknown fields** at every level. 3. Update `updated` on every changed task. 4. Write atomically: write `tasks.json.tmp` in the same folder, then rename over `tasks.json`. Python snippet: ```python import json, os, secrets, time p = "{{WORKSPACE}}/tasks.json" d = json.load(open(p)) now = time.time() d["tasks"].append({"id": "t_" + secrets.token_hex(3), "title": "Call the accountant", "notes": "", "status": "todo", "priority": 1, "due": None, "project_id": None, "topic_path": None, "labels": [], "created": now, "updated": now, "done_at": None, "order": max([t.get("order", 0) for t in d["tasks"]] + [0]) + 1000}) tmp = p + ".tmp"; json.dump(d, open(tmp, "w"), indent=2, ensure_ascii=False); os.replace(tmp, p) ```
## Answering questions "What is due today?" -> tasks with `status != done` and `due <= today` (in the configured time zone, `maxxing status`/config), overdue first, then by priority. Quote titles, keep it short.
Intended uses
- Use Maxxing Tasks when this documented workflow matches the task.
Implementation notes
- Review the source instructions and adapt inputs before running the workflow.
Try it, then tell us how it went
A copied prompt does not tell us whether the task worked. Report your result after checking the output. We collect your tool and outcome, never your files or prompt.