Superset Agent Standup
superset-sh/superset
Sweeps every Superset workspace, task and agent terminal to report what finished, what needs review and what is blocked, read-only, and can publish the digest as a page.
File-based to-do tracking for multi-step and multi-session work.
Install Task Tracking
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a claude-codeProject install by default; add -g for ~/.claude/skills/.
$ gh skill install ntorga/agent-starter-kit task-tracking --agent claude-codeProject scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .claude/skills && cp -r skills-src/skills/task-tracking .claude/skills/task-tracking && rm -rf skills-srcUse ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.
Claude Code skills documentation · loads skills from .claude/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .claude/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$skill-installer install https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-trackingType this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a codexProject install goes to .agents/skills/; add -g for ~/.codex/skills/.
$ gh skill install ntorga/agent-starter-kit task-tracking --agent codexProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .agents/skills && cp -r skills-src/skills/task-tracking .agents/skills/task-tracking && rm -rf skills-srcUse ~/.agents/skills/ instead of .agents/skills for a personal install.
Codex skills documentation · loads skills from .agents/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .agents/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a cursorProject install goes to .agents/skills/; add -g for ~/.cursor/skills/.
$ gh skill install ntorga/agent-starter-kit task-tracking --agent cursorProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/skills/task-tracking .cursor/skills/task-tracking && rm -rf skills-srcUse ~/.cursor/skills/ instead of .cursor/skills for a personal install.
Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .cursor/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gemini skills install https://github.com/ntorga/agent-starter-kit.git --path skills/task-tracking--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a gemini-cliProject install goes to .agents/skills/; add -g for ~/.gemini/skills/.
$ gh skill install ntorga/agent-starter-kit task-tracking --agent gemini-cliProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/skills/task-tracking .gemini/skills/task-tracking && rm -rf skills-srcUse ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.
Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .gemini/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ gh skill install ntorga/agent-starter-kit task-trackingInstalls for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a github-copilotProject install goes to .agents/skills/; add -g for ~/.copilot/skills/.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .github/skills && cp -r skills-src/skills/task-tracking .github/skills/task-tracking && rm -rf skills-srcUse ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.
GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .github/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
$ npx skills add ntorga/agent-starter-kit --skill task-tracking -a opencodeOpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.
$ gh skill install ntorga/agent-starter-kit task-tracking --agent opencodeProject scope by default (.agents/skills/); add --scope user for a personal install.
$ git clone --depth 1 https://github.com/ntorga/agent-starter-kit.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/skills/task-tracking .opencode/skills/task-tracking && rm -rf skills-srcUse ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.
OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/
Install the "task-tracking" agent skill from https://github.com/ntorga/agent-starter-kit/tree/main/skills/task-tracking into .opencode/skills/task-tracking/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "task-tracking", then confirm the skill loads.OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.
Facts
- Skill name
task-tracking- GitHub stars
- 146
- Token cost
- ~949 tokens
- SKILL.md length
- 451 words
- Files
- 1
- Skills in repo
- 21
- Repo updated
- First seen
- Licence
- MIT
At a glance
File-based to-do tracking for multi-step and multi-session work.
- Works in 5 steps: Check for an existing to-do. Run ls… → Create a to-do from the plan or task… → Update as you go. After completing each… → …
- Tasks that involve Task management
- SKILL.md covers Purpose, Procedure, Schema and Schema notes, plus 1 more section
- Instructions only: no scripts, shell commands, URLs or credentials in SKILL.md
What it does
Task Tracking is an agent skill from ntorga/agent-starter-kit. File-based to-do tracking for multi-step and multi-session work.
Its SKILL.md is about 950 tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.
It sits in Productivity & Automation, covering Task management. The repository describes itself as: The scaffold for your multi-model, personalized Natural Language AI Harness (NLAH) . The licence is MIT.
When your agent uses it
- Tasks that involve Task management
Example prompts
- “/task-tracking”
Workflow steps
5 steps, taken from the first numbered list in SKILL.md.
- Check for an existing to-do. Run ls .memory/todo/ 2>/dev/null to list existing to-do files. If a to-do file for the current task already…
- Create a to-do from the plan or task brief. If no existing to-do matches, run the following command to create the file — replace the…
- Update as you go. After completing each item, mark it [x] and add a log entry if the outcome was notable (unexpected decision, deviation…
- Handle blockers. If an item cannot be completed, mark it [-] with a reason in the log. Continue with unblocked items. If nothing can…
- Close the to-do. When all items are done (or skipped with reason), truncate the to-do file with : > .memory/todo/. The handoff summary is…
What it can do on your machine
Read from SKILL.md and the folder at commit 851e942. It shows what the files ask for, not the result of running them.
Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
No scripts in the folder and no shell commands in SKILL.md (its code samples are bash and markdown).
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names no API keys, tokens, secrets or passwords.
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.
Context cost
Task Tracking loads about 949 tokens when it runs. Until then it costs about 20 tokens; SKILL.md has 451 words of instructions outside code blocks.
Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.
Safety
Auto-check passed
The automated check found no risky patterns in SKILL.md.
Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.
SKILL.md
The full file from ntorga/agent-starter-kit at commit 851e942, republished under its MIT licence (© ntorga). 451 words, ~949 tokens.
Download SKILL.mdSave it as
.claude/skills/task-tracking/SKILL.md (or your agent's skills folder).- name
- task-tracking
- description
- File-based to-do tracking for multi-step and multi-session work.
- usedBy
- all
- version
- 0.1.4
- lastUpdated
- 2026-09-12
Purpose
Agents working on multi-step tasks need a way to track progress that survives session boundaries. A task that spans hours or days will be picked up by an agent with no memory of what was already done. This skill defines a file-based to-do format that any persona can create, update, and resume — so the next session starts where the last one stopped.
Procedure
Check for an existing to-do. Run
ls .memory/todo/ 2>/dev/nullto list existing to-do files. If a to-do file for the current task already exists, read it and resume from the first unchecked item. Do not recreate.Create a to-do from the plan or task brief. If no existing to-do matches, run the following command to create the file — replace the placeholders with real values:
bash mkdir -p .memory/todo && cat > .memory/todo/YYYY-MM-DD-<prefix>-<slug>.md << 'TEMPLATE' # <Task Title> **Slug:** <prefix>-<slug> **Source:** plan | task-brief **Created:** YYYY-MM-DD **Updated:** YYYY-MM-DD ## Items - [ ] First item - [ ] Second item ## Log - YYYY-MM-DD: Created from plan/task-brief. TEMPLATEThen populate the items from
impl.mdepics and file lists, or from the task brief's acceptance criteria. Each item must be a concrete, verifiable action — not a vague category.Target directory:
.memory/todo/— always at the project root, never anywhere else.Naming convention: The filename uses the pattern
YYYY-MM-DD-<prefix>-<slug>.md, where<prefix>is the conventional-commit type and<slug>is a short kebab-case summary — the same convention used for branch names (follows:rules/git.md). Examples:.memory/todo/2026-02-18-feat-user-auth.md,.memory/todo/2026-02-18-fix-login-redirect.md. If a git branch already exists for this work, derive the prefix and slug from the branch name.Update as you go. After completing each item, mark it
[x]and add a log entry if the outcome was notable (unexpected decision, deviation from plan, blocker encountered). Do not batch updates — mark items done as they finish.Handle blockers. If an item cannot be completed, mark it
[-]with a reason in the log. Continue with unblocked items. If nothing can proceed, stop and note the blocker in the log.Close the to-do. When all items are done (or skipped with reason), truncate the to-do file with
: > .memory/todo/<filename>. The handoff summary is the permanent record — the to-do is a working document, not an archive.
Show full SKILL.md (123 more words)Show less
Schema
# <Task Title>
**Slug:** <prefix>-<topic>
**Source:** plan | task-brief
**Created:** YYYY-MM-DD
**Updated:** YYYY-MM-DD
## Items
- [x] Completed item
- [ ] Pending item
- [-] Skipped item
## Log
- YYYY-MM-DD: Notable event, decision, or blocker.Schema notes
- Slug matches the
<prefix>-<topic>portion of the filename and follows the git branch prefix convention. - Source identifies whether items came from an architect plan or a task brief.
- Updated changes every time an item is checked off or a log entry is added.
- Items use standard checkbox syntax:
[x]done,[ ]pending,[-]skipped. - Log entries are chronological. Keep them terse — one line per event.
Guardrails
- To-do files live exclusively in
.memory/todo/at the project root. Never create them anywhere else. - Never start implementing without first creating or locating an existing to-do.
- Never let the to-do drift from reality. If you completed something, mark it now, not later.
- Never delete a to-do with unchecked items unless the task has been explicitly cancelled.
© ntorga, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file
Files
Just SKILL.md in skills/task-tracking of ntorga/agent-starter-kit.
Open the folder on GitHubat commit 851e942
Compare with similar skills
Task Tracking next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.
| Skill | Stars | Used in | Tokens | Auto-check | Licence | Repo updated |
|---|---|---|---|---|---|---|
| Task Tracking this skillntorga/agent-starter-kit | 146 | — | ~949 | Automated safety check: Pass | MIT | |
| Superset Agent Standupsuperset-sh/superset | 15k | — | ~712 | Automated safety check: Pass | Custom licence | |
| AgentRQ Workspace Agentagentrq/agentrq | 1.1k | — | ~1.9k | Automated safety check: Pass | AGPL-3.0 | |
| Markdown Task Managerioniks/MarkdownTaskManager | 535 | — | ~2.2k | Automated safety check: Pass | MPL-2.0 | |
| Pi Messenger Crewnicobailon/pi-messenger | 719 | — | ~3.7k | Automated safety check: Pass | None | |
| Codekanban CLIfy0/CodeKanban | 225 | — | ~2.7k | Automated safety check: Pass | Apache-2.0 |
Similar skills
AgentRQ Workspace Agent
agentrq/agentrq
Guides a workspace agent through executing assigned tasks, replying to a remote human operator, and creating sub-tasks, memory and events inside an AgentRQ workspace.
Markdown Task Manager
ioniks/MarkdownTaskManager
A skill your agent uses when managing tasks, the system is a Kanban task manager based on local Markdown files (kanban.md and archive.md).
Pi Messenger Crew
nicobailon/pi-messenger
Orchestrator reference for pi-messenger Crew planning, task management, configuration, and agent coordination.
Codekanban CLI
fy0/CodeKanban
Operate CodeKanban workflows, terminal sessions, and web sessions through the installable codekanban-cli command.
Kanban Tui
Zaloog/kanban-tui
Comprehensive kanban board and task management via ktui CLI.
More from ntorga/agent-starter-kit
All 21 skills in this repoAgent Decision
ntorga/agent-starter-kit
Deterministic self-evaluation rubric for decision escalations — scored every run using the FRAME framework.
Agent Memory
ntorga/agent-starter-kit
Long-term and session memory across sessions. An agent skill from ntorga/agent-starter-kit.
Architect Design Tree
ntorga/agent-starter-kit
Builds the design tree for the grill — decisions mapped as nodes with dependencies, recommendations, and impact, pruned by path.
Architect Impl Grounding
ntorga/agent-starter-kit
Grounds the grill's settled decisions in the codebase — annotates impl.md with file paths, signatures, reference files, test specs, and LOC; re-grounds the next epic after each landing.
Boot
ntorga/agent-starter-kit
Session startup — gitignore, auto-update, memory, rules, context, CLI config, and greet.
Browser Inspect
ntorga/agent-starter-kit
Browser inspection and interaction for verifying rendered web UI during development.
Related
Questions about Task Tracking
What does Task Tracking do?
File-based to-do tracking for multi-step and multi-session work. Task Tracking is an agent skill from ntorga/agent-starter-kit. File-based to-do tracking for multi-step and multi-session work.
When should I use Task Tracking?
Task Tracking fits situations like: tasks that involve Task management.
How do I install Task Tracking in Claude Code?
Run `npx skills add ntorga/agent-starter-kit --skill task-tracking -a claude-code`. Or copy the skill folder (skills/task-tracking in ntorga/agent-starter-kit) into .claude/skills/task-tracking in your project. Claude Code loads it when a task matches its description.
How do I install Task Tracking in Codex?
Run `npx skills add ntorga/agent-starter-kit --skill task-tracking -a codex`. Or copy the skill folder (skills/task-tracking in ntorga/agent-starter-kit) into .agents/skills/task-tracking in your project. Codex loads it when a task matches its description.
Can I use Task Tracking in Cursor, Gemini CLI or GitHub Copilot?
Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add ntorga/agent-starter-kit --skill task-tracking -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/task-tracking, .gemini/skills/task-tracking, .github/skills/task-tracking and .opencode/skills/task-tracking in your project.
What does Task Tracking need to run?
SKILL.md names no scripts, command-line tools or credentials: Task Tracking is instructions for the agent only.
Does Task Tracking access the network?
SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.
Is Task Tracking safe to install?
Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.
What licence does Task Tracking use?
Task Tracking is published under the MIT licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.
How many tokens does Task Tracking use?
About 949 tokens (SKILL.md is roughly 3.8k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.
What are the alternatives to Task Tracking?
Skills that share tags, products or a category with Task Tracking: Superset Agent Standup (superset-sh/superset, 15k stars), AgentRQ Workspace Agent (agentrq/agentrq, 1.1k stars), Markdown Task Manager (ioniks/MarkdownTaskManager, 535 stars) and Pi Messenger Crew (nicobailon/pi-messenger, 719 stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.
Who maintains Task Tracking?
ntorga (a GitHub user) maintains it in ntorga/agent-starter-kit, which has 146 GitHub stars. The repository holds 21 skills in this directory. The repository was last updated on September 12, 2026.
Source: ntorga/agent-starter-kit on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.