Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/rvk7895/llm-knowledge-basesnpx agentmods add skills/rvk7895/llm-knowledge-bases/kbWrote 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/kb)<a href="https://agentmods.dev/skills/rvk7895/llm-knowledge-bases/kb"><img src="https://agentmods.dev/badge/skills/rvk7895/llm-knowledge-bases/kb/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/kb"><img src="https://agentmods.dev/badge/skills/rvk7895/llm-knowledge-bases/kb.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 | $0.00080 | $0.09193 |
| Opus 5 | $0.00040 | $0.04596 |
| Sonnet 5 | $0.00016 | $0.01839 |
| Haiku 4.5 | $0.00008 | $0.00919 |
Grade A, and why
kb 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 9d 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 — 679 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Overview
Main operating skill for LLM-maintained knowledge bases. Five workflows: compile, query, lint, evolve, reflect. All opus-orchestrated with model-aware subagent dispatch.
First action in every invocation: read kb.yaml from the project root. If missing, tell the user to run kb-init and stop.
Report Preferences
After reading kb.yaml, extract the report_preferences: block. These are free-text prose instructions the user set via kb-init or /kb-preferences, controlling how outputs are written (audience, register, depth, code_handling, diagrams, self_containment, citations, argument_iteration, notes).
Apply to all generated prose:
- Compile: preferences shape how new wiki articles are written — register, self-containment, depth of per-article profiles, diagram choices in article bodies.
- Query: preferences shape the final answer prose and any new wiki articles auto-evolved from the query.
- Lint / Evolve / Reflect: preferences shape the output report prose (lint reports, evolve suggestions), not the mechanical checks themselves.
If report_preferences: is missing: fall back to factory defaults in plugins/kb/references/report-style-guide.md silently. Mention it once in the first output of the session: "No report_preferences set — using factory defaults. Run /kb-preferences init to customize."
Per-task overrides. If the user's current request explicitly contradicts a stored preference, follow the request for this task only. Do NOT modify kb.yaml — reflection handles persistence.
Reflection at end of compile and query
After a compile or query finishes writing its output, run a lightweight reflection step — only propose preference updates for high-confidence signals:
- User explicitly asked you to "remember" something
- User corrected the same style choice twice in the conversation
- User gave clear feedback directly tied to the output just produced
Follow the Reflection Protocol in plugins/kb/skills/kb-preferences/SKILL.md. On approval, write updates to kb.yaml and log to .meta/_preference_history.md with trigger reflection after /kb compile (or /kb query). Skip silently otherwise.
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.
- 9d ago First seen · 679 lines · 80 tokens per session scan A 2e3ee2acdb00
kb is a skill published in the GitHub repository rvk7895/llm-knowledge-bases (36 stars, last pushed 2mo ago), licensed MIT. It adds 80 tokens to every session and 9,193 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 2026-08-30.
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.