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/sandbaseai/sandbase-skills/task-managementnpx skills add sandbaseai/sandbase-skills --skill task-managementgit clone --depth 1 https://github.com/sandbaseai/sandbase-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/sandbaseai/sandbase-skills/task-management)<a href="https://agentmods.dev/skills/sandbaseai/sandbase-skills/task-management"><img src="https://agentmods.dev/badge/skills/sandbaseai/sandbase-skills/task-management.svg" alt="Measured on agentmods" height="20"></a>What 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 5.1 | $0.00037 | $0.00628 |
| Opus 5 | $0.00018 | $0.00314 |
| Sonnet 5 | $0.00007 | $0.00126 |
| Haiku 4.5 | $0.00004 | $0.00063 |
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 — 85 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Task Management
Tasks are tracked in a simple TASKS.md file that both you and the user can edit.
When task sources are supplied as web pages, read the SandBase API map and use only the capabilities listed there. Resolve each current input schema with sandbase_describe_tool before calling it through sandbase_call_tool.
File Location
Always use TASKS.md in the current working directory.
- If it exists, read it and make only user-requested edits
- If it doesn't exist, offer the template below; create it when the user asks to add or manage tasks
Optional Dashboard
If the project already provides a task dashboard, it may be used with the same
TASKS.md file. Do not create or copy dashboard assets unless the user requests
that separately and a valid source asset is available.
Format & Template
When creating a new TASKS.md, use this exact template (without example tasks):
# Tasks
## Active
## Waiting On
## Someday
## Done
Task format:
- [ ] **Task title** - context, for whom, due date- Sub-bullets for additional details
- Completed:
- [x] ~~Task~~ (date)
How to Interact
When user asks "what's on my plate" / "my tasks":
- Read TASKS.md
- Summarize Active and Waiting On sections
- Highlight anything overdue or urgent
When user says "add a task" / "remind me to":
- Add to Active section with
- [ ] **Task**format - Include context if provided (who it's for, due date)
When user says "done with X" / "finished X":
- Find the task
- Change
[ ]to[x] - Add strikethrough:
~~task~~ - Add completion date
- Move to Done section
When user asks "what am I waiting on":
- Read the Waiting On section
- Note how long each item has been waiting
Conventions
- Bold the task title for scannability
- Include "for [person]" when it's a commitment to someone
- Include "due [date]" for deadlines
- Include "since [date]" for waiting items
- Sub-bullets for additional context
- Keep completed items for at least ~1 week; clear or archive them only when the user requests it
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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 · 85 lines · 37 tokens per session scan A 36ea43ae3de0
task-management is a skill published in the GitHub repository sandbaseai/sandbase-skills (126 stars, last pushed 2d ago), licensed Apache-2.0. It adds 37 tokens to every session and 628 once invoked, about $0.0002 per session on Opus 5. 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 2026-09-03.
Other skills, from other repositories
grill-me
Grill the user about a requirement, decision, or idea before implementation, then produce an actionable planning report without writing code. Use when the user wants to clarify requirements, stress-test an idea, compare approaches, or plan before coding.
deepseek-harness-docker
Deploy, configure, verify, upgrade, and troubleshoot DeepSeek Harness with the community Docker, Docker Compose, and Helm runtime, including the built-in Chromium/noVNC browser and optional plugin market. Use when users ask to run DSH or DeepSeek Harness locally or on Kubernetes, mount a writable workspace, configure…
triage
Label-based issue triage workflow. Use when a batch of issues needs sorting by priority/type, or the task mentions "triage", "分流", "prioritize issues", "label". Pulls issues, classifies them, and applies labels/assignees via gh.
yao-board
Kanban board and task query expert. ALWAYS invoke this skill when the user asks about boards, tasks, task status, or project progress. Do not guess task state — use this skill first.
dsh-skill-dev
当需要给 DeepSeek Harness 写一个技能、调试技能没被发现的问题、或决定某个能力该做成技能还是插件时使用——覆盖 frontmatter 规则、发现路径、fail-closed 陷阱和自测方法。.
error-handling
当需要设计错误处理、决定该抛还是该返回、写错误信息、或排查"出错了但没人知道"的问题时使用——按调用方是否需要区分处理来决定错误的结构。.