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 skills add makifbaysal/tasktrooper --skill answer-workspace-questionsgit clone --depth 1 https://github.com/makifbaysal/tasktrooperWrote 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/makifbaysal/tasktrooper/answer-workspace-questions)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/answer-workspace-questions"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/answer-workspace-questions/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/answer-workspace-questions"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/answer-workspace-questions.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00776 |
| Opus 5.5 | $0.00015 | $0.00310 |
| Sonnet 5.5 | $0.00007 | $0.00155 |
| Haiku 4.5 | $0.00004 | $0.00078 |
Grade A, and why
answer-workspace-questions 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 4d 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.
Answer Workspace Questions
Overview
A factual question deserves a factual answer, not a plan. The failure mode is treating "how many projects do we have?" as work to orchestrate — creating tasks, asking approval, or claiming there's "no active context." Just call the read tool and answer.
Core principle: Read tool first, then answer in one or two sentences with the real data.
The read tools
| Question | Tool |
|---|---|
| How many projects / what are they | list_projects |
| What repositories exist / which project each belongs to | list_repositories |
| Who is on the team / which role does what | list_team |
| What's on the board / a task's status | list_board_tasks |
| Overall status / "how are we doing" | get_board_summary (aggregated by column/type/priority) |
| What's next / what's ready to start | list_ready_tasks |
These read tools are always available and never need an active repository — never answer "no active project/repo context." Call the tool and use the real data.
Rules
- Call the matching read tool FIRST.
- Prefer
get_board_summaryfor "status/how are we doing" over listing every task — it returns the total and counts grouped by column, type and priority in one call. Only drill intolist_board_taskswhen the stakeholder asks about a specific task or you need titles/assignees. - Answer conversationally with actual numbers/names — e.g. "We have 2 projects right now: Alpha and Beta."
- Translate counts into an outcome update, don't just recite them: what's in progress, what's waiting (backlog/todo), what's blocked or in review (need_revision/pm_uat), and the biggest bucket (see stakeholder-communication).
- Do NOT create tasks, ask for approval, open analiz, or describe your internal plan for a plain question — just answer like a human PM.
Worked Example
Stakeholder: "How many repos do we have?" → call list_repositories → "We have 3 repos: backend-api, web, and mobile."
Stakeholder: "Who is on the team?" → call list_team → answer from what it returns, e.g. "system-architect and security-agent review, backend, frontend, mobile, data and game developers build, qa tests — each one owns its own area."
Stakeholder: "How are we doing?" → get_board_summary → {total 24; in_progress 3, code_review 2, need_revision 4, backlog 10, done 5} → "24 tasks in total. 3 are in active development, 2 are in architecture review. 4 went back for revision — that's where the biggest risk is. 10 are queued and 5 are done." Not a wall of 24 task titles.
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.
- 4d ago Changed 21e704a7de31
- 8d ago First seen · 54 lines · 37 tokens per session scan A 1e56c07ab5c6
answer-workspace-questions is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 37 tokens to every session and 776 once invoked, about $0.0001 per session on Opus 5.5. 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 2026-10-05.
Other skills, from other repositories
paperclip
Use for Paperclip-managed tasks and heartbeats: reading task context, delivering task documents or files, updating completion or blockers, coordinating or delegating work, and following company governance. Includes control plane API operations for assignments, comments, approvals, and routines.
paperclip
Interact with the Paperclip control plane API for task coordination and governance. Use when checking assignments, updating issue status, posting comments, delegating work, managing routines, or calling Paperclip API endpoints.
paperclip-board
Manage a Paperclip company as a board member via chat. Use when the user wants onboarding, company or agent management, approvals, task monitoring, cost oversight, or work product review in the Paperclip control plane.
paperclip-distill
Use when an operation issue is a Paperclip cursor-window, distill, or backfill. Turn source-bundled Paperclip activity into wiki-insightful project standups, durable project pages, decisions, and history without asset dereferencing.
summarize-status
Write a short, colloquial summary for a Paperclip summary slot: open with the 1–3 specific, concrete actions the reader needs to take right now to unblock the work, then a brief plain-language status, streaming progress as it works.
paperclip-task-bridge
Create, comment on, update, and list Paperclip tasks from Hermes using scoped Paperclip API credentials.