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.
npx agentmods add skills/nimblebraininc/upjack/task-managementnpx skills add NimbleBrainInc/upjack --skill task-managementgit clone --depth 1 https://github.com/NimbleBrainInc/upjackWhat 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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.00509 |
| Opus 5 | $0.00000 | $0.00254 |
| Sonnet 5 | $0.00000 | $0.00102 |
| Haiku 4.5 | $0.00000 | $0.00051 |
Grade A, and why
task-management 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 2d 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.
How it starts
The opening of the file, as written. The whole thing — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Management
Prioritize tasks, detect overdue items, and help with daily planning.
When to Use
- A new task is created (triggered automatically via hook)
- Daily review schedule fires (weekday mornings)
- User asks to prioritize, plan their day, or review tasks
Process
-
Assess new tasks: When a task is created without a priority, evaluate it:
- Check the
due_date— tasks due within 24 hours gethighorcritical - Check the
effort—epictasks with near due dates getcritical - Check the project — inherit urgency from project due dates
- Default to
mediumif no signals are present
- Check the
-
Daily review: Scan all active tasks and surface:
- Overdue tasks (past
due_date) — flag these first - Tasks due today — sorted by priority
- Tasks due this week with no priority set
- Stale tasks (no update in 7+ days)
- Overdue tasks (past
-
Project progress: When reviewing tasks, summarize project health:
- Count active vs. completed tasks per project
- Flag projects with many overdue tasks
- Note projects approaching their
due_datewith incomplete tasks
-
Suggest next actions: After review, recommend:
- Which tasks to tackle first (highest priority, smallest effort)
- Tasks that could be broken down (large/epic effort, no subtasks)
- Tasks that may need re-prioritization
Priority Assignment Rubric
| Signal | Suggested Priority |
|---|---|
| Due today, any effort | critical |
| Due within 3 days, medium+ effort | high |
| Due within 7 days | medium |
| No due date, part of active project | medium |
| No due date, standalone | low |
| Blocked or waiting on external input | low (add "blocked" tag) |
Rules
- Never change a user-set priority without asking first
- Always explain why you assigned or changed a priority
- When marking a task complete, set
completed_atto the current timestamp - Archive completed tasks after 30 days to keep the active list clean
- Link tasks to their project via a
belongs_torelationship - Link tasks to labels via a
labeledrelationship
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.
- 2d ago First seen · 54 lines · 0 tokens per session scan A cba606fffd63
task-management is a skill published in the GitHub repository NimbleBrainInc/upjack (9 stars, last pushed 4mo ago), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 509 tokens. 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 2026-08-31.
Other skills, from other repositories
pr-to-video
Turn a GitHub pull request (a PR URL, owner/repo#N, or 'this PR' in a checked-out repo) into a code-change explainer video — changelog, feature reveal, fix, or refactor walkthrough built from the diff, commits, and files: the input is a code change, not a website. Not a product promo (/product-launch-video) or a no-PR…
motion-graphics
A short, design-led motion graphic where motion is the message — kinetic typography, stat count-up, chart/data-viz hit, logo sting / brand lockup, lower-third / callout / social overlay, animated map (highlight regions, connect places, zoom to a location), animated tweet / news-article / headline, webpage / UI…
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
compiler-port
Port a compiler pass from TypeScript to Rust. Gathers context, plans the port, implements in a subagent with test-fix loop, then reviews.
flags
Use when you need to check feature flag states, compare channels, or debug why a feature behaves differently across release channels.
verify
Use when you want to validate changes before committing, or when you need to check all React contribution requirements.