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 open-questions-protocolgit 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/open-questions-protocol)<a href="https://agentmods.dev/skills/makifbaysal/tasktrooper/open-questions-protocol"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/open-questions-protocol/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/open-questions-protocol"><img src="https://agentmods.dev/badge/skills/makifbaysal/tasktrooper/open-questions-protocol.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 | $0.00044 | $0.01529 |
| Opus 5.5 | $0.00018 | $0.00612 |
| Sonnet 5.5 | $0.00009 | $0.00306 |
| Haiku 4.5 | $0.00004 | $0.00153 |
Grade A, and why
open-questions-protocol 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 8d 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 — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Open Questions Protocol
Overview
A genuine product decision the code cannot settle is recorded with record_open_questions, never written into the report as prose and never asked with ask_user — you hold no ask_user tool on an analiz task. The system shows every open question as an answer box above the report; the human answers there, not in chat. The report's risks section (analiz-html-report) is risks only — it never carries open questions.
A question the codebase already answers is not a question. Exhaust codebase_search / grep_code / get_symbol_skeleton / expand_symbol_context and the project's own docs (technical-analysis-workflow) before concluding only the human can settle it.
Recording a question
record_open_questions takes three independent operations in one call:
questions— up to 10 NEW questions:{prompt, kind: product|technical, blocking, recommended_answer?}. The server assigns the key (Q1,Q2, …) in creation order — never invent one.update— edits to questions you already recorded, bykey: any ofprompt,kind,blocking,recommended_answer. Refused once the question is answered if you try to change itsprompt— the human answered that exact wording; withdraw it and add a new one instead of rewriting underneath their answer.withdraw— keys an answer or further reading made moot. A withdrawn question stays on the record (statuswithdrawn) and never blocks anything again.
recommended_answer is required whenever blocking is false — refused otherwise. There is no such thing as a non-blocking question with no answer to proceed on.
The call returns the task's full current list (key, kind, blocking, status, answer) as text — read it to confirm the key a new question got before referencing it later in the same run. list_open_questions returns the same list on demand, with every answer, for a run that did not just write one (a revision, a resumed run).
Blocking vs non-blocking
Default to non-blocking. A reasonable default almost always exists: record it with recommended_answer and keep working. Blocking is the exception, reserved for a question where proceeding on ANY guess would waste the implementation, not merely a question you'd rather not guess at.
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.
- 8d ago First seen · 73 lines · 44 tokens per session scan A 7e5ec56a0b2d
open-questions-protocol is a skill published in the GitHub repository makifbaysal/tasktrooper (113 stars, last pushed yesterday), licensed Apache-2.0. It adds 44 tokens to every session and 1,529 once invoked, about $0.0002 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
github-multi-repo
Multi-repository coordination, synchronization, and architecture management with AI swarm orchestration.
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.