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 agentmods add skills/davidmatousek/tachi/kb-createnpx skills add davidmatousek/tachi --skill kb-creategit clone --depth 1 https://github.com/davidmatousek/tachiWrote 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/davidmatousek/tachi/kb-create)<a href="https://agentmods.dev/skills/davidmatousek/tachi/kb-create"><img src="https://agentmods.dev/badge/skills/davidmatousek/tachi/kb-create.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 | $0.00073 | $0.03775 |
| Opus 5 | $0.00036 | $0.01887 |
| Sonnet 5 | $0.00015 | $0.00755 |
| Haiku 4.5 | $0.00007 | $0.00378 |
Grade A, and why
kb-create scanned grade A with 1 finding 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 5d 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl http://localhost:3000/health Copies of this mod
1 near-identical copy found in the catalogue:
- kb-create — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 632 lines — stays where its author put it; the contents beside it link to each section on GitHub.
KB Create Skill
Purpose
Guided pattern and bug creation with interactive prompts, automatic quality validation, and improvement suggestions. Ensures high-quality KB entries that meet institutional knowledge standards.
Decision Tree: Pattern vs Bug
Should I create a PATTERN or BUG entry?
START: Do you have a reusable solution or specific error fix?
↓
Is this a specific error with an exact error message?
→ YES: Is the solution configuration/environment-specific?
→ YES: Create BUG entry
→ NO: Could be either - is it reusable across projects?
→ YES: Create PATTERN
→ NO: Create BUG
→ NO: Is this a general solution to a common problem?
→ YES: Create PATTERN
→ NO: Is it a design decision or architectural guidance?
→ YES: Create PATTERN
→ NO: Maybe not KB-worthy - consider documentation instead
Pattern: Reusable solutions, design patterns, best practices, architectural guidance Bug: Specific errors with exact error messages, environment issues, configuration fixes
Pattern Creation Workflow
Step 1: Collect Basic Information
Creating new KB Pattern
Required fields (asterisk = required):
* Title (10-100 characters):
→ Example: "PostgreSQL Connection Pool Optimization"
* Category (select one):
1. ARCH (Architecture & Design)
2. DB (Database)
3. API (API Design)
4. AUTH (Authentication)
5. SECURITY (Security)
6. TEST (Testing)
7. PERF (Performance)
8. FRONTEND (Frontend)
9. INFRA (Infrastructure)
10. DEPLOY (Deployment)
11. CACHE (Caching)
12. MCP (MCP Servers)
13. CLIENT (Client Integration)
14. FLOW (Workflows)
→ Your choice (1-14):
* Keywords (min 5, comma-separated):
→ Example: postgresql, connection-pool, optimization, performance, scaling
→ Your keywords:
Step 2: Define Problems Solved
* Problems this pattern solves (min 2, max 10):
Problem 1:
→ Example: Connection pool exhaustion under high load
Problem 2:
→ Example: Slow query performance due to connection limits
Problem 3 (or Enter to continue):
→ Example: Connection timeout errors during peak traffic
... (continue until Enter on empty line)
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.
- 5d ago First seen · 632 lines · 73 tokens per session scan A 634b8084e3de
kb-create is a skill published in the GitHub repository davidmatousek/tachi (90 stars, last pushed 22d ago), licensed Apache-2.0. It adds 73 tokens to every session and 3,775 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
container-image-scan
USAP agent skill for Container Image Scan. Use for classifying container-image vulnerability scan findings from Trivy, Grype, or Snyk into a block-deploy, fix-by-SLA-window, track, or accept decision across base-image OS packages, application dependencies, and unexpected image layers.
security-requirements-review
USAP agent skill for Security Requirements Review. Use for proactive analysis of design documents — POA&M, PRDs, architecture docs, requirements specs — to extract security gaps before any alerts fire.
cloud-security-posture
USAP agent skill for Cloud Security Posture. Use for Evaluate cloud misconfigurations and posture drift.
attack-surface-management
USAP agent skill for Attack Surface Management. Use for Continuously discover and assess exposed assets.
behavioral-analytics
USAP agent skill for Behavioral Analytics (UEBA). Use for Analyze behavioral anomalies across users and entities.
secrets-exposure
USAP agent skill for Secrets and Credential Exposure Detection. Use for scanning repositories, pipelines, and runtime environments for exposed secrets, API keys, tokens, and credentials — includes entropy analysis, blast-radius estimation, and revocation prioritization.