Borrowing it
Nothing to install: this file belongs to zkysar1/Claude-Mind. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/zkysar1/Claude-Mind/main/.claude/skills/open-questions/SKILL.mdgit clone --depth 1 https://github.com/zkysar1/Claude-MindWrote 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/zkysar1/claude-mind/open-questions)<a href="https://agentmods.dev/skills/zkysar1/claude-mind/open-questions"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/open-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/zkysar1/claude-mind/open-questions"><img src="https://agentmods.dev/badge/skills/zkysar1/claude-mind/open-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Output Handling · line 148 Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.Fix: Set explicit limits on output length, generation count, and rate. Use max_tokens and truncation to prevent unbounded output.
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 | $0.00098 | $0.02732 |
| Opus 5 | $0.00049 | $0.01366 |
| Sonnet 5 | $0.00020 | $0.00546 |
| Haiku 4.5 | $0.00010 | $0.00273 |
Grade A, and why
open-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 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 — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/open-questions — User Dashboard
Shows what needs the user's attention: pending questions the agent logged, goals assigned to the user, and blocked goals grouped by reason. Primes context first so follow-up discussion is informed by domain knowledge.
USER-ONLY COMMAND. Claude MUST NEVER invoke this skill autonomously. Valid from ANY state (RUNNING, IDLE, UNINITIALIZED).
Step 0: Load Conventions — Bash: load-conventions.sh with each name from the conventions: front matter. Read only the paths returned (files not yet in context). If output is empty, all conventions already loaded — proceed to next step.
Phase 1: Prime Context
1. Invoke /prime
— Loads Self, guardrails, reasoning bank, category-specific knowledge
— If UNINITIALIZED and /prime outputs "Nothing to prime": SKIP (continue to Phase 2)
Phase 2: Scan Pending Questions (FLEET-WIDE)
This dashboard answers "what does the USER owe / what is waiting on them" — a question about the WHOLE FLEET, not the bound agent. Both steps below are required: fixing either alone still leaves the user blind (g-115-3074).
1. Refresh every agent's mirror (DATA leg — defeats stale/absent peer files):
Bash: `bash core/scripts/owncloud-pull.sh --all-agents --only pending-questions.yaml`
→ ~1s fleet-wide. `--only` is load-bearing: the unfiltered fleet pull is a
full continuity sweep at ~59s/agent (~5min), which is not a viable cost for
an interactive dashboard. Fleet roster comes from team-state.
→ Best-effort: on a non-own-cloud backend this is a no-op, and a per-agent
failure is isolated (the sweep continues). NEVER block the dashboard on it —
a failed refresh degrades to reading whatever mirrors exist, which is
strictly better than showing nothing. Proceed to step 2 regardless.
2. Read every agent's questions (SKILL leg — defeats bound-agent-only scope):
Bash: `bash core/scripts/pending-questions-read.sh --all-agents --status pending`
→ JSON array of pending entries, each tagged with an `agent` key. Store as
pending_questions list; group by `agent` for output.
This reader is shape-tolerant (flattens the dict-wrapper / list-with-wrapper /
bare / mixed on-disk shapes via the same _load_questions logic the sweep
sibling uses, rb-1786) and applies that SAME flattener per agent file. Do NOT
hand-roll a naive top-level `status == "pending"` scan of the raw YAML — it
silently SKIPS entries nested inside a `{questions: [...]}` wrapper
(g-115-3039) — and do NOT hand-roll a fleet walk either: the flatten body is
kept byte-faithful across three lock-step copies, and a fourth copy in skill
pseudocode is the least likely to be kept in sync. A missing or malformed
per-agent file contributes [] without failing the others.
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 Changed · +1 lines 4bcd6409a46a
- 10d ago First seen · 221 lines · 98 tokens per session scan A 44c1739dd1c5
open-questions is a skill published in the GitHub repository zkysar1/Claude-Mind (5 stars, last pushed 2d ago), licensed MIT. It adds 98 tokens to every session and 2,732 once invoked, about $0.0005 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 2026-08-31.
Other skills, from other repositories
cron-management
Skill for reading and writing cron.md in the correct format for scheduled LLM or command tasks. Use when: editing cron.md, adding or changing cron schedules, or removing periodic jobs.
zoom-meeting-scribe
A listen-only note-taking workflow for Zoom meetings. It receives live transcript sections, organizes what was said, and prepares a report after the meeting ends.
notion-tool
Notion integration tool for searching, reading, creating, and updating pages and databases via the API. Use when: editing Notion pages, adding database rows, or searching a workspace.
chatwork-tool
Chatwork integration tool for send/receive messages, search, unreplied checks, and room listing. Use when: posting to Chatwork, listing rooms, checking unreplied threads, searching messages, or handling mentions.
discord-tool
Discord integration tool for messaging, search, guild and channel listing, and reactions. Use when: posting to Discord, listing channels, searching messages, or adding reactions in guilds.
google-calendar-tool
Google Calendar integration tool for listing and creating events via OAuth2 Calendar API access. Use when: checking upcoming events, creating appointments, or updating your schedule.