kb-query

kb-query is a skill for Claude Code from davidmatousek/tachi. It costs 70 tokens per session (2,480 once invoked), scanned A, original, Apache-2.0.

An interactive search tool for a team's knowledge base, using ordinary language to find documented patterns and bug fixes.

In plain words
What is it for?
Use it to find solutions for problems such as database connection issues, authentication, caching, or other previously documented engineering work.
Why use it?
It reduces the need to remember exact titles or keywords by ranking likely matches and showing their quality scores.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Install

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.

agentmods
npx agentmods add skills/davidmatousek/tachi/kb-query
Any agent
npx skills add davidmatousek/tachi --skill kb-query
Clone the repo
git clone --depth 1 https://github.com/davidmatousek/tachi

Made for: Claude Code.

Wrote 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.

agentmods badge for kb-query

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidmatousek/tachi/kb-query.svg)](https://agentmods.dev/skills/davidmatousek/tachi/kb-query)
Your own site
<a href="https://agentmods.dev/skills/davidmatousek/tachi/kb-query"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/kb-query.svg" alt="Measured on agentmods" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,480 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.02480
Opus 5 $0.00035 $0.01240
Sonnet 5 $0.00014 $0.00496
Haiku 4.5 $0.00007 $0.00248

Measured 6d ago against content hash 2566d849b386, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

kb-query 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 6d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • kb-query — 100% identical, 0 lines differ
.claude/skills/kb-query/SKILL.md · 392 lines

How it starts

The opening of the file, as written. The whole thing — 392 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB Query Skill

Purpose

Interactive Knowledge Base search with natural language queries, providing fast access to institutional knowledge through relevance-ranked results with quality scoring.

How It Works

Step 1: Accept Query

User provides search query or problem description:

User: "Search KB for database connection pool issues"

Step 2: Execute Search

Run KB search with intelligent parameters:

# Basic search
make kb-search QUERY="database connection pool"

# With category filter
make kb-search QUERY="JWT authentication" CATEGORY=AUTH

# With quality threshold
make kb-search QUERY="performance optimization" MIN_SCORE=70

# All parameters
make kb-search QUERY="redis cache" CATEGORY=CACHE MIN_SCORE=60 LIMIT=10

Step 3: Display Results

Show top results with relevance and quality scores:

Search Results for "database connection pool"

Found 3 patterns:

1. DB-005: PostgreSQL Connection Pool Optimization
   Category: DB | Quality: 85/100 | Relevance: 9.2/10
   Keywords: postgresql, connection-pool, optimization, performance
   Problems solved:
   - Connection pool exhaustion under load
   - Slow query performance due to connection limits

2. PERF-002: Connection Pool Tuning Guide
   Category: PERF | Quality: 78/100 | Relevance: 8.5/10
   Keywords: connection-pool, tuning, performance, scalability
   Problems solved:
   - Optimizing pool size for workload
   - Monitoring pool utilization

3. DB-002: Database Connection Retry Logic
   Category: DB | Quality: 72/100 | Relevance: 7.1/10
   Keywords: database, connection, retry, error-handling
   Problems solved:
   - Transient connection failures
   - Graceful degradation on DB issues

Step 4: Offer Actions

Interactive follow-up options:

Actions:
1. View full content of a pattern (enter 1-3)
2. Search with different parameters
3. Browse by category
4. Exit

Your choice:

Step 5: View Full Content (if requested)

Display complete pattern details:

# Read full pattern file
cat docs/kb/patterns/DB-005-postgresql-connection-pool.md

Read the full file on GitHub · 392 lines

Changes

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.

  1. 6d ago First seen · 392 lines · 70 tokens per session scan A 2566d849b386

Subscribe to this mod's changes

kb-query is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 23d ago), licensed Apache-2.0. It adds 70 tokens to every session and 2,480 once invoked, about $0.0003 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.