company-kb

company-kb is a skill for Claude Code from oyi77/1ai-skills. It costs 22 tokens per session (4,197 once invoked), scanned A, original, MIT.

A company-specific knowledge base for storing information about products, clients, team members, procedures, decisions, and operations.

In plain words
What is it for?
It helps track company entities, document procedures, record decisions, and connect work to organizational context.
Why use it?
It keeps organization-wide facts and history in one place so agents and people can find consistent answers.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: built for gbrain.

Part of the 1ai-skills plugin — 209 skills, 4 commands shipped together

Good fit It helps track company entities, document procedures, record decisions, and connect work to organizational context.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/oyi77/1ai-skills/company-kb
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.

Any agent
npx skills add oyi77/1ai-skills --skill company-kb
Clone the repo
git clone --depth 1 https://github.com/oyi77/1ai-skills

Made for: Claude Code.

Or install 1ai-skills, the plugin that ships this one along with the rest of its 209 skills, 4 commands.

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 company-kb

README.md
[![agentmods](https://agentmods.dev/badge/skills/oyi77/1ai-skills/company-kb/github.svg)](https://agentmods.dev/skills/oyi77/1ai-skills/company-kb)
Your own site
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/company-kb"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/company-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.

agentmods 80×15 button for company-kb

Your own site · 80×15
<a href="https://agentmods.dev/skills/oyi77/1ai-skills/company-kb"><img src="https://agentmods.dev/badge/skills/oyi77/1ai-skills/company-kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,197 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 44
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
How audits are shown
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 $0.00022 $0.04197
Opus 5 $0.00011 $0.02099
Sonnet 5 $0.00004 $0.00839
Haiku 4.5 $0.00002 $0.00420

Measured 2d ago against content hash 0c45286cde74, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

company-kb 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 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.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

subprocess.run([
core/core/company-kb/SKILL.md · 414 lines

How it starts

The opening of the file, as written. The whole thing — 414 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Company KB — Quick Reference

Role: The Company Knowledge Base (company-kb) stores organization-specific memory — products, services, team members, clients, procedures, and operational history. While the parent kb skill manages the PARA structure and general knowledge retrieval, company-kb specializes in entity tracking, company-wide procedures, agent accountability records, and cross-referencing decisions to organizational context. Both agents and humans use this to maintain a single source of truth.

When to Use

  • An org fact must survive sessions: product inventory, client accounts, team roster, vendor contracts
  • A decision needs recorded context and alternatives so the "why" is recoverable later
  • A recurring task needs a step-by-step procedure others can follow
  • Agent sessions must be accountable: what ran, what it did, what facts it added
  • A query spans entities ("which clients run the affected product?") — traverse the links graph
  • Critical entity changes should be recallable cross-session via the 1ai-hub brain

Overview

The Python helpers need PyYAML — install with pip install pyyaml.

company-kb is the organization-wide memory layer: structured YAML entities for products, clients, team, decisions, operations, vendors, procedures, and projects, linked into a navigable entity graph via the links field. Agents register entities, record decisions with rationale and alternatives, log session accountability, and cross-reference decisions to organizational context. It complements the parent kb skill (PARA structure, general retrieval) and pushes critical changes to the 1ai-hub brain for cross-session recall.

Organization Structure

Maintain a consistent directory layout so every agent and human can navigate without guessing:

~/kb/company/
├── products/              # Products and services (one dir per product)
│   └── agent-platform/entity.yaml
├── clients/               # Client accounts, contacts, contracts
├── team/                  # Team members, roles, skills
├── decisions/             # ADRs and policy decisions with rationale
├── operations/            # Session logs, runbooks, monitoring configs
├── vendors/               # Third-party tools, services, contracts
├── procedures/            # Step-by-step SOPs for recurring tasks
├── projects/              # Active and completed project records
└── index.yaml             # Cross-entity references and tag index

Read the full file on GitHub · 414 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 Changed · +36 lines 0c45286cde74
  2. 9d ago First seen · 378 lines · 22 tokens per session scan A 55d4a6a208a6

Subscribe to this mod's changes

company-kb is a skill published in the GitHub repository oyi77/1ai-skills (12 stars, last pushed today), licensed MIT. It adds 22 tokens to every session and 4,197 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.