knowledge-base-update

A skill for recording important project knowledge in structured files for future agents. It covers decisions, coding conventions, bug causes and fixes, third-party service quirks, and research findings.

In plain words
What is it for?
Use it after making an architectural decision, fixing a non-obvious bug, discovering an API limitation, establishing a project convention, or completing substantial research.
Why use it?
It prevents useful discoveries from being lost or researched again later. Entries are stored in the project's knowledge base and updated when the topic already exists.

Skill for Claude CodeCodex

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/omergocmen/vibe-coder-kit/knowledge-base-update
Any agent
npx skills add omergocmen/vibe-coder-kit --skill knowledge-base-update
Clone the repo
git clone --depth 1 https://github.com/omergocmen/vibe-coder-kit

Made for: Claude Code, Codex.

Per session 75 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,009 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 $0.00075 $0.01009
Opus 5 $0.00037 $0.00504
Sonnet 5 $0.00015 $0.00202
Haiku 4.5 $0.00007 $0.00101

Measured 2d ago against content hash 9adc0ea3b5a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

knowledge-base-update 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 2d 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.

.agent/skills/knowledge-base-update/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Update Skill

When to Trigger

Activate this skill when any of the following occur:

  • An architectural or tech-stack decision is made (and the why matters)
  • A non-obvious bug is fixed (root cause + fix documented)
  • A 3rd-party service/API has a quirk, limit, or gotcha discovered
  • A project convention is established (naming, folder structure, patterns)
  • A research question is answered after significant investigation
  • A "we tried X and it failed because Y" moment happens

Step-by-Step Process

1. Identify the Entry Type

Choose the category that best describes what was learned:

Type When to Use
decision Architecture, tech choices, trade-offs
convention Naming rules, code patterns, folder structures
bug Root cause + fix for a non-obvious problem
gotcha 3rd-party quirk, env issue, edge case trap
research Answer to a question requiring significant investigation

2. Determine the File Path

Write to: .agent/knowledge/<slug>.md

  • slug = kebab-case summary of the topic (e.g., auth-token-refresh-strategy)
  • If an entry for this topic already exists, update it rather than creating a new file
  • Group related topics under subfolders: .agent/knowledge/auth/, .agent/knowledge/infra/, etc.

3. Write the Entry

Use this exact template:

---
type: <decision|convention|bug|gotcha|research>
topic: <Short human-readable title>
date: <YYYY-MM-DD>
tags: [<tag1>, <tag2>]
---

## Summary
<One or two sentences — what was learned, bottom line up front>

## Context
<Why this came up. What problem were we solving?>

## Decision / Finding
<The actual content. Be specific. Include code snippets if helpful.>

## Rationale
<Why this choice over alternatives. What alternatives were rejected and why.>

## Consequences
<What does this affect going forward? What to watch out for?>

## References
- <File path, PR link, conversation snippet, or external URL>

Read the full file on GitHub · 120 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. 2d ago First seen · 120 lines · 75 tokens per session scan A 9adc0ea3b5a8

Subscribe to this mod's changes

knowledge-base-update is a skill published in the GitHub repository omergocmen/vibe-coder-kit (91 stars, last pushed 2mo ago), licensed MIT. It adds 75 tokens to every session and 1,009 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.

Related

Other skills, from other repositories

tdd

Use for every coding task. Enforce strict TDD workflow: activate Serena, investigate first, clarify+confirm requirements, write per-task REQUIREMENTS.md in .requirements/ /, verify APIs via web search, then implement in tiny test-verified steps.

Shelpuk-AI-Technology-Consulting/agent-skill-tdd · 59 tokens

electron-desktop-builder

Converts a web app (Express, React, Vite, Next.js) into an Electron desktop app. Use when starting a new Electron project from an existing web app, when setting up electron-builder for the first time, when creating main.ts/preload.ts boilerplate, when generating icon assets, or when configuring NSIS installers.…

smartbrainactivity/electron-desktop-builder · 109 tokens

ai-skill-auditor

A universal, dependency-free Node.js tool to statically audit AI Skills and local agents for malicious patterns.

smartbrainactivity/smartbrain-skill-auditor · 28 tokens

design

Comprehensive design skill: brand identity, design tokens, UI styling, logo generation (55 styles, Gemini or Atlas Cloud AI), corporate identity program (50 deliverables, CIP mockups), HTML presentations (Chart.js), banner design (22 styles, social/ads/web/print), icon design (15 styles, SVG, Gemini 3.1 Pro), social…

nextlevelbuilder/ui-ux-pro-max-skill · 144 tokens

ui-styling

Create beautiful, accessible user interfaces with shadcn/ui components (built on Radix UI + Tailwind), Tailwind CSS utility-first styling, and canvas-based visual designs. Use when building user interfaces, implementing design systems, creating responsive layouts, adding accessible components (dialogs, dropdowns…

nextlevelbuilder/ui-ux-pro-max-skill · 90 tokens

banner-design

Design banners for social media, ads, website heroes, creative assets, and print. Multiple art direction options with optional generated or supplied visuals. Actions: design, create, generate banner. Platforms: Facebook, Twitter/X, LinkedIn, YouTube, Instagram, Google Display, website hero, print. Styles: minimalist…

nextlevelbuilder/ui-ux-pro-max-skill · 99 tokens