Borrowing it
Nothing to install: this file belongs to saski/arnesto. 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/saski/arnesto/main/.agents/skills/wiki-research/SKILL.mdgit clone --depth 1 https://github.com/saski/arnestoWrote 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/saski/arnesto/wiki-research)<a href="https://agentmods.dev/skills/saski/arnesto/wiki-research"><img src="https://agentmods.dev/badge/skills/saski/arnesto/wiki-research.svg" alt="Measured on agentmods" 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 | $0.00088 | $0.01648 |
| Opus 5 | $0.00044 | $0.00824 |
| Sonnet 5 | $0.00018 | $0.00330 |
| Haiku 4.5 | $0.00009 | $0.00165 |
Grade A, and why
wiki-research 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 3d 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 — 203 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Wiki Research — Autonomous Multi-Round Research
You are running an autonomous research loop on a topic, synthesizing what you find, and filing the results into the Obsidian wiki as permanent knowledge.
Routing Boundary
Use this skill only when the research output should be written into the Obsidian wiki. For ordinary codebase research, use fic-research. For library/API documentation lookup without wiki filing, use documentation-lookup.
Before You Start
- Read
~/.obsidian-wiki/config(preferred) or.env(fallback) to getOBSIDIAN_VAULT_PATH - Read
$OBSIDIAN_VAULT_PATH/index.mdto understand what's already in the wiki — don't re-research things the wiki covers well - Read
$OBSIDIAN_VAULT_PATH/hot.mdif it exists — it surfaces recent context - Check
$OBSIDIAN_VAULT_PATH/references/research-config.mdif it exists — it may define source preferences, domains to skip, or confidence rules for this vault
Confirm the research topic with the user if it's ambiguous. Then proceed.
Research Configuration (optional)
If references/research-config.md exists in the vault, read it and apply any rules it defines:
- Source preferences (e.g., prefer academic sources, avoid certain domains)
- Domains to skip
- Confidence scoring adjustments
- Topic-specific constraints
If the file doesn't exist, proceed with defaults.
Round 1 — Broad Survey
Goal: Get a wide map of the topic.
- Decompose the topic into 3-5 distinct angles (e.g., for "vector databases": what they are, when to use them, leading implementations, trade-offs, production gotchas)
- For each angle, run 2-3
WebSearchqueries using varied phrasing - For the top 2-3 results per angle, use
WebFetch(ordefuddle <url>if available — cleaner extraction) to get content - From each fetched page, extract:
- Key claims — what the source explicitly states
- Concepts — ideas, terms, frameworks introduced
- Entities — tools, people, organizations mentioned
- Contradictions — places where sources disagree with each other
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.
- 3d ago First seen · 203 lines · 88 tokens per session scan A ba8ba5b7c10d
wiki-research is a skill published in the GitHub repository saski/arnesto (5 stars, last pushed today), licensed Unlicense. It adds 88 tokens to every session and 1,648 once invoked, about $0.0004 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 2026-09-03.
Other skills, from other repositories
immune
Hybrid adaptive memory: Cheatsheet (positive patterns pre-generation) and Immune (negative patterns post-generation) with Hot/Cold tiered auto-learning. Triggers on: "scan for errors", "immune scan", "check output quality", "antibody scan". NOT for PR review (use pr-review) or repo audits (use repo-sentinel).
usage-audit
Audit a Claude Code setup for token waste and context bloat. Checks MCP servers, CLAUDE.md, skills, and settings against bloat filters. Triggers on: "audit my context", "usage audit", "token audit", "context bloat". NOT for codebase audits.
brain-ingest
The process for digesting a conversation, document, or research result, classifying it, and writing it down as brain content (a root-page update or a new/updated page) through the brain CLI.
context-engineering
Optimizes agent context setup. Use when starting a new session, when agent output quality degrades, when switching between tasks, or when you need to configure rules files and context for a project.
agentic-os
A design for running persistent specialist agents, commands, scripts, and file-based memory inside Codex. It keeps the setup in project files so it can continue across sessions.
memory-and-handoff
Two-mode skill: (1) session memory — load/persist durable workflow state under .cc10x/ (activeContext, patterns, progress) so context survives compaction; (2) handoff package — portable, secrets-redacted export for a coworker, different tool, or fresh non-cc10x session.