Borrowing it
Nothing to install: this file belongs to guzus/ai-research-arm. 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/guzus/ai-research-arm/main/.agents/skills/expand-llm-wiki/SKILL.mdgit clone --depth 1 https://github.com/guzus/ai-research-armWrote 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/guzus/ai-research-arm/expand-llm-wiki)<a href="https://agentmods.dev/skills/guzus/ai-research-arm/expand-llm-wiki"><img src="https://agentmods.dev/badge/skills/guzus/ai-research-arm/expand-llm-wiki/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/guzus/ai-research-arm/expand-llm-wiki"><img src="https://agentmods.dev/badge/skills/guzus/ai-research-arm/expand-llm-wiki.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00099 | $0.01216 |
| Opus 5 | $0.00049 | $0.00608 |
| Sonnet 5 | $0.00020 | $0.00243 |
| Haiku 4.5 | $0.00010 | $0.00122 |
Grade A, and why
expand-llm-wiki 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 12d 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 — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Expand LLM Wiki
Use this skill to grow ARA's compounding LLM wiki without corrupting its graph. The wiki is not regenerated. It is CRUD-maintained: update existing pages by default, create new pages only when the subject is genuinely missing, and never delete pages.
First Principles Check
Before writing, answer these briefly for yourself:
- What is actually being asked: latest digest ingest, topic backfill, graph cleanup, schema repair, or OKF export readiness?
- What are the mechanics: Markdown pages under
research/wiki/, strict frontmatter, alias-aware[[wikilinks]], generatedindex.json, append-onlylog.md. - What is known directly: facts already in the daily digest, model tickets, or cited repo sources.
- What is assumed: unsourced claims, vendor benchmarks, rumored timelines, or anything only inferred from community chatter.
Challenge the premise if the requested expansion would duplicate pages, read the raw firehose instead of curated synthesis, or turn weak signal into a permanent wiki page.
Required Context
Read these before editing:
docs/wiki-schema.mdin full. It is the contract.research/wiki/index.mdandresearch/wiki/log.md.- The relevant existing pages under
research/wiki/{entities,concepts,themes}/. - The curated input for the task:
- Latest or specified
research/digest/*-digest.md. - Relevant
research/models/tickets/*.md, especially recently updated tickets. - For an explicit topic backfill, any repo-local research files the user points at.
- Latest or specified
Do not crawl research/twitter/, research/rss/, research/community/,
research/blogs/, research/arxiv/, or other raw-source directories for a
normal expansion pass. The digest exists to curate those sources. Use web search
only to corroborate a specific unstable claim or when the user explicitly asks
for current external verification.
Expansion Workflow
- Rank candidate subjects. Pull out significant entities, concepts, and themes. Ignore passing mentions. For manual backfills, prefer 4-8 high-leverage subjects over shallow coverage.
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.
- 12d ago First seen · 141 lines · 99 tokens per session scan A 209e7e4f84a3
expand-llm-wiki is a skill published in the GitHub repository guzus/ai-research-arm (11 stars, last pushed yesterday), licensed MIT. It adds 99 tokens to every session and 1,216 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
install-loop
Install Loop Engineering into a project via the unified CLI front door (@cobusgreyling/loop). Prefer this over invoking loop-init / loop-audit separately. Week-one is report-only; never enable auto-merge or unattended fixes unless the human explicitly asks and doctor is healthy.
pr-review-triage
Watch open PRs, check CI status, review staleness, merge conflicts, and unanswered review comments. Produces a prioritized watchlist.
loop-verifier
Independent verification agent for loop-produced changes. Finds reasons to reject. Runs tests. Confirms diff scope. Use after minimal-fix or any implementer sub-agent — never in the same role as the implementer.
changelog-scan
Scan merged PRs and commits since a given reference, extract titles, labels, types, and signals. Produces structured input for release notes drafting.
dependency-triage
Scan package manifests and lockfiles for outdated and vulnerable dependencies. Classify by severity and update type.
issue-triage
Scan open issues and discussions, deduplicate, prioritize, and propose labels. Provides a clean actionable queue.