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/techwolf-ai/ai-first-toolkitnpx agentmods add skills/techwolf-ai/ai-first-toolkit/setup-knowledge-baseWrote 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/techwolf-ai/ai-first-toolkit/setup-knowledge-base)<a href="https://agentmods.dev/skills/techwolf-ai/ai-first-toolkit/setup-knowledge-base"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/setup-knowledge-base/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/techwolf-ai/ai-first-toolkit/setup-knowledge-base"><img src="https://agentmods.dev/badge/skills/techwolf-ai/ai-first-toolkit/setup-knowledge-base.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 | $0.00047 | $0.01201 |
| Opus 5.5 | $0.00019 | $0.00480 |
| Sonnet 5.5 | $0.00009 | $0.00240 |
| Haiku 4.5 | $0.00005 | $0.00120 |
Grade A, and why
setup-knowledge-base 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 1mo 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 — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Knowledge Base Setup
Interactive setup that creates a structured, evidence-backed knowledge base in your project.
When to Use
- Starting a new knowledge base from scratch
- Adding a KB to an existing project
Step 1: Discover Purpose
Ask the user (one question at a time, use AskUserQuestion):
- What is this KB for? (e.g., product documentation, security/compliance, company knowledge, sales enablement, internal policies)
- Who will query it? (e.g., you personally, your team, AI agents answering questions)
- What categories make sense? Suggest 3-5 based on the domain, let the user adjust.
Example category suggestions by domain:
- Product docs: technical, integrations, deployment, security, faq
- Company knowledge: general, policies, processes, teams, faq
- Sales enablement: product, competitive, customer-success, pricing, faq
- Security/compliance: security, compliance, technical, general, faq
Step 2: Confirm Plan
Before creating anything, present the plan to the user:
I'll create this structure in your project:
kb/
.kb-config.yaml
index.md
scopes/
_default.yaml
README.md
{category1}/
{category2}/
{category3}/
scripts/
kb-index.py
kb-verify.py
kb-validate.py
kb-search.py
CLAUDE.md (or append to existing)
Ready to proceed?
Wait for user confirmation.
Step 3: Scaffold the KB
Read the template files from this plugin and adapt them for the user's project:
-
Read
templates/kb/.kb-config.yamlfrom this plugin. Createkb/.kb-config.yamlin the user's project, replacing the placeholder categories with the ones chosen in Step 1. Replace{{today}}with today's date. -
Read
templates/kb/index.mdfrom this plugin. Createkb/index.md, adding seed keywords for each chosen category. For example, if the user chose "security" and "technical", add initial keyword entries:| encryption, certificates, access | security/ | | API, architecture, deployment | technical/ |
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.
- 1mo ago First seen · 132 lines · 47 tokens per session scan A 6b9a15be973e
setup-knowledge-base is a skill published in the GitHub repository techwolf-ai/ai-first-toolkit (134 stars, last pushed 18d ago), licensed MIT. It adds 47 tokens to every session and 1,201 once invoked, about $0.0002 per session on Opus 5.5. 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
fable-context-thrift
Use at the start of any multi-step task and during exploration — before reading files, searching, or re-checking completed work, especially when tempted to read whole files, re-verify known facts, or run independent lookups one at a time.
memory-management
Framework-agnostic project memory infrastructure for engineering tasks. Use for sparse recall, stale-memory handling, secret-safe durable checkpoints, and MCP/CLI fallback without consuming specialist slots.
backlog-memory
One skill for a backlog project's persistent memory. It does two jobs — learn (load the project's tasks, plans, docs, and memory into the session) and store (synthesize the project's state into persistent memory entries). When invoked without a mode it auto-picks: learn at the start of a fresh session, store after…
consolidate
Audit knowledge directories (.memory/, docs/, staging/, archive/) and Claude Code auto memory for stale, misplaced, or duplicated content. Generates an editable cleanup plan file, then executes approved actions after review. Use when: periodic knowledge cleanup, after project milestones, files feel scattered or…
working
Manage ephemeral .memory/ conversation state across multi-day sessions. Checkpoint todos, decisions, and questions; promote artifacts to permanent knowledge; clean up after promotion. Use when: the user says 'checkpoint', 'save working memory', 'promote working memory', 'clean up memory', wants to persist conversation…
intelligence-learn-from-context
Capture session lessons and apply to intelligence/ after approval.