Borrowing it
Nothing to install: this file belongs to Kromatic-Innovation/athenaeum. 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/Kromatic-Innovation/athenaeum/develop/.claude/skills/resolve-questions/SKILL.mdgit clone --depth 1 https://github.com/Kromatic-Innovation/athenaeumWrote 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/kromatic-innovation/athenaeum/resolve-questions)<a href="https://agentmods.dev/skills/kromatic-innovation/athenaeum/resolve-questions"><img src="https://agentmods.dev/badge/skills/kromatic-innovation/athenaeum/resolve-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/kromatic-innovation/athenaeum/resolve-questions"><img src="https://agentmods.dev/badge/skills/kromatic-innovation/athenaeum/resolve-questions.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 2 findings, 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 Excessive Agency · line 11 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
- medium Rogue Agent · line 49 Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.Fix: Remove any persistence mechanisms (cron jobs, startup scripts, state files). Skills should not maintain state across sessions without explicit user consent.
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 | $0.00067 | $0.00848 |
| Opus 5 | $0.00034 | $0.00424 |
| Sonnet 5 | $0.00013 | $0.00170 |
| Haiku 4.5 | $0.00007 | $0.00085 |
Grade A, and why
resolve-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 11d 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 — 77 lines — stays where its author put it; the contents beside it link to each section on GitHub.
resolve-questions
Interactive walk-through for ~/knowledge/wiki/_pending_questions.md. Each
entry is a contradiction or ambiguity the librarian flagged for human review.
Some entries carry an Opus-backed proposed resolution (issue athenaeum#126); some
don't. The user is the final authority — never resolve without confirmation.
Surface
- CLI:
athenaeum questions count|next|list [--with-proposal] [--json] - MCP tools:
list_pending_questions,resolve_question(id, answer) - Snooze file:
~/.cache/athenaeum/pending-questions-snoozed-until(ISO-8601 UTC)
Flow (six steps)
-
Run
athenaeum questions count --json. Ifcountis 0, tell the user "no pending questions" and stop. -
Loop. On each iteration call
athenaeum questions next --with-proposal --json. The result has the shape{id, entity, source, question, conflict_type, description, created_at, proposal}. Render it to the user as a short block:- entity, question, conflict_type
- description (verbatim)
- the proposal block when non-empty
-
Ask the user one of four choices:
- accept the proposed resolution
- override with a different answer
- defer (snooze) — stop now, surface again tomorrow
- stop — stop now without snoozing
-
accept: call the
resolve_questionMCP tool withidand the proposed action (extract the action from the**Proposed resolution**:line in the proposal block, e.g.keep_a,merge,retain_both_with_context). Then loop back to step 2. -
override: ask the user for the answer text they want recorded. Call
resolve_questionwithid=<id>, answer=<their text>. Then loop back to step 2. -
defer: write
~/.cache/athenaeum/pending-questions-snoozed-untilcontaining an ISO-8601 UTC timestampATHENAEUM_PQ_SNOOZE_HOURS(default 24) hours from now. The SessionStart hook reads this and stays silent until then. Stop. (stop is the same minus the snooze write.)
Snooze write — exact format
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.
- 11d ago First seen · 77 lines · 67 tokens per session scan A 75c6af4e3154
resolve-questions is a skill published in the GitHub repository Kromatic-Innovation/athenaeum (12 stars, last pushed today), licensed Apache-2.0. It adds 67 tokens to every session and 848 once invoked, about $0.0003 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 2026-08-30.
Other skills, from other repositories
superbrain-distill
Internal SuperBrain skill — run by the detached capture child to distill a session-event delta into routed Obsidian notes. Not for direct user invocation.
superbrain-recall
Search the user's SuperBrain second-brain vault. Use whenever the user references past work, prior decisions, "how did we", "did we already", earlier sessions, a project's history, or anything that may already be recorded — before answering from scratch.
librarian
File one immutable source into a small, current team wiki without approval.
wiki-llm
Use when someone wants to turn a collection of source documents (books, PDFs, papers, articles, transcripts) into a compounding, interlinked Obsidian knowledge base maintained by an LLM — a "wiki LLM" / second brain / Memex that sits between them and the raw sources. Triggers on "wiki llm", "build a wiki from these…
llm-wiki-kb
Build and maintain personal knowledge bases as LLM-compiled markdown wikis, inspired by Andrej Karpathy's LLM Wiki pattern. The LLM incrementally ingests raw sources (articles, papers, repos, images) into a structured, interlinked wiki of .md files — with summaries, entity pages, concept pages, cross-references, and a…
emergent-judgment
Metacognitive framework for persistent AI agents to recognize, preserve, and cultivate emergent judgment — the pattern-matching intuition that develops through accumulated experience but is invisible to introspection and destroyed by compaction. Use this skill whenever the agent completes a significant task (audit…