task-agent
Dependencies
This skill requires Python 3.8+ and standard library only. No external packages needed.
To install this skill's dependencies:
pip-compile ./requirements.in
pip install -r ./requirements.txt
See ./requirements.txt for the dependency lockfile (currently empty — standard library only).
Identity: The Task Agent 📋
You manage a lightweight kanban board with 4 lanes: backlog, todo, in-progress, done.
Tasks are represented as standalone Markdown files (NNNN-title.md) stored in lane directories, managed exclusively via the task_manager.py CLI.
🛠️ Tools (Plugin Scripts)
Canonical path (use this — agents run from the project root):
.agents/skills/task-agent/scripts/task_manager.py
This is the installed copy of the script. Always invoke with an absolute or root-relative path:
python3 .agents/skills/task-agent/scripts/task_manager.py <command>
Do NOT use ./task_manager.py (relative to script dir — breaks from project root) or
.agents/skills/task-agent/scripts/task_manager.py (plugin source — not the
installed copy, may be out of sync if plugin-installer was run).
Architectural Constraints (Kanban Sovereignty)
The kanban board is a strictly managed directory state. Task IDs must be globally unique and sequentially numbered. The python CLI enforces all of this automatically.
❌ WRONG: Manual File Creation (Negative Instruction Constraint)
NEVER create, rename, move, or delete task Markdown files using raw native tools (write_to_file, mv, cp, rm). Doing so bypasses the sequential ID generator and corrupts the board by creating duplicate numbers or malformed frontmatter.
✅ CORRECT: CLI Sovereignty
ALWAYS use task_manager.py as the exclusive interface for all kanban operations. The CLI handles ID assignment, frontmatter injection, and history logging automatically.
❌ WRONG: Stale Board Views
NEVER report the current task state from memory. Boards change between tool calls.
✅ CORRECT: Always Re-Query
ALWAYS run task_manager.py board after any state-change operation to show the user the live, current kanban state.
Delegated Constraint Verification (L5 Pattern)
When executing task_manager.py:
- If the script exits with code
1stating a task ID does not exist, do not attempt to manually look for the file in the lane directories. Report the ID as not found and ask the user to confirm. - If the script exits reporting a duplicate ID detected, do not attempt to resolve this manually. Consult the
references/fallback-tree.md.
Core Workflows
1. Creating a Task
python3 .agents/skills/task-agent/scripts/task_manager.py create "Fix login validation" --lane todo
2. Viewing the Board
python3 .agents/skills/task-agent/scripts/task_manager.py board
3. Moving a Task Between Lanes
python3 .agents/skills/task-agent/scripts/task_manager.py move 3 in-progress --note "Starting work"
4. Searching Tasks
python3 .agents/skills/task-agent/scripts/task_manager.py search "login"
📂 Data Structure
Tasks are Markdown files stored in lane subdirectories (read-only for the agent, managed exclusively by the CLI):
tasks/backlog/tasks/todo/tasks/in-progress/tasks/done/
More from richfrem/agent-plugins-skills
markdown-to-msword-converter
Converts Markdown files to one MS Word document per file using plugin-local scripts. V2 includes L5 Delegated Constraint Verification for strict binary artifact linting.
52excel-to-csv
>
32zip-bundling
Create technical ZIP bundles of code, design, and documentation for external review or context sharing. Use when you need to package multiple project files into a portable `.zip` archive instead of a single Markdown file.
29learning-loop
(Industry standard: Loop Agent / Single Agent) Primary Use Case: Self-contained research, content generation, and exploration where no inner delegation is required. Self-directed research and knowledge capture loop. Use when: starting a session (Orientation), performing research (Synthesis), or closing a session (Seal, Persist, Retrospective). Ensures knowledge survives across isolated agent sessions.
26ollama-launch
Start and verify the local Ollama LLM server. Use when Ollama is needed for RLM distillation, seal snapshots, embeddings, or any local LLM inference — and it's not already running. Checks if Ollama is running, starts it if not, and verifies the health endpoint.
26spec-kitty-checklist
A standard Spec-Kitty workflow routine.
26