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 rvk7895/llm-knowledge-bases --skill researchgit clone --depth 1 https://github.com/rvk7895/llm-knowledge-basesWrote 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/rvk7895/llm-knowledge-bases/research)<a href="https://agentmods.dev/skills/rvk7895/llm-knowledge-bases/research"><img src="https://agentmods.dev/badge/skills/rvk7895/llm-knowledge-bases/research/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/rvk7895/llm-knowledge-bases/research"><img src="https://agentmods.dev/badge/skills/rvk7895/llm-knowledge-bases/research.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 | $0.00028 | $0.01061 |
| Opus 5 | $0.00014 | $0.00531 |
| Sonnet 5 | $0.00006 | $0.00212 |
| Haiku 4.5 | $0.00003 | $0.00106 |
Grade A, and why
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 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 — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attribution: Originally authored by Weizhena. Included with attribution for use in the Deep query workflow.
Research Skill - Preliminary Research
Trigger Method
/research <topic>
Execution Flow
Step 1: Generate Initial Framework Using Model's Internal Knowledge
Based on the topic, use the model's existing knowledge to generate:
- A list of main research objects/items in the field
- A suggested framework of research fields
Output {step1_output} and use AskUserQuestion to confirm:
- Does the items list need additions or removals?
- Does the field framework meet the requirements?
Step 2: Web Search Supplement
Use AskUserQuestion to inquire about the time range (e.g., last 6 months, 2024 to present, no limit).
Parameter Collection:
{topic}: Research topic input by user{YYYY-MM-DD}: Current date{step1_output}: Complete output content generated in Step 1{time_range}: Time range specified by user
Hard Constraint: The following prompt must be strictly reproduced, only replacing variables in {xxx}, no rewriting of structure or wording allowed.
Launch 1 web-search-agent (background), Prompt Template:
prompt = f"""## Task
Research Topic: {topic}
Current Date: {YYYY-MM-DD}
Based on the following preliminary framework, supplement the latest items and recommended research fields.
## Existing Framework
{step1_output}
## Objectives
1. Verify if existing items miss important objects
2. Supplement items based on missing objects
3. Continue searching for {topic}-related items within {time_range} and supplement
4. Supplement new fields
## Output Requirements
Return structured results directly (do not write files):
### Supplemented Items
- item_name: Brief explanation (why should it be included)
...
### Recommended Additional Fields
- field_name: Field description (why this dimension is needed)
...
### Information Sources
- [Source 1](url1)
- [Source 2](url2)
"""
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.
- 8d ago First seen · 145 lines · 28 tokens per session scan A a53c98486c16
research is a skill published in the GitHub repository rvk7895/llm-knowledge-bases (36 stars, last pushed 2mo ago), licensed MIT. It adds 28 tokens to every session and 1,061 once invoked, about $0.0001 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
link-memory
Use after important user-approved decisions, when durable context should be proposed or reviewed, and for explicit Link memory lifecycle work: remember, recall, review, update, archive, restore, forget, or explain local memories through the CLI without requiring MCP.
link-retrieve
Use before answering work that may depend on user memory, project history, source-backed notes, or prior decisions; retrieve compact Link context through the CLI without loading the whole wiki or requiring MCP.
link-health
Use at the start of Link work when readiness is unclear, after installs or upgrades, and before repairs; verify health, inspect interrupted writes, back up, and repair generated indexes without MCP.
link-ingest
Use when raw files are present, source pages look stale, or a user asks to ingest notes into Link; refresh source-backed wiki pages, propose memories, and validate updates through the CLI without MCP.
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.