install-kb-agent

A setup wizard for building a domain-specific knowledge-base agent. A knowledge base stores information in an organized form so an agent can search, connect, and update it.

In plain words
What is it for?
Use it to create knowledge bases for areas such as customer support research, clinical research, legal analysis, community management, or personal notes.
Why use it?
It turns an interview about your subject area into a prepared information system, reducing the need to design its structure and supporting tools manually.

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/abilityai/abilities/kb-agent
Any agent
npx skills add Abilityai/abilities --skill kb-agent
Clone the repo
git clone --depth 1 https://github.com/Abilityai/abilities

Made for: Claude Code, Codex.

Per session 52 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 18,175 The whole file, excluding the scripts and references it only reads on demand.
Security scan D 2 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 $0.00052 $0.18175
Opus 5 $0.00026 $0.09087
Sonnet 5 $0.00010 $0.03635
Haiku 4.5 $0.00005 $0.01818

Measured 2d ago against content hash 9ddbf4b77deb, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade D, and why

install-kb-agent scanned grade D with 2 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.

Reads agent configuration directoriesmediumAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

# Container-only config: the Trinity base image bakes ~/.claude/settings.json with

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

rm -rf "$TMPDIR"
plugins/create-agent/skills/kb-agent/SKILL.md · 1,523 lines

How it starts

The opening of the file, as written. The whole thing — 1,523 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Install KB Agent

ℹ️ First, set expectations: before anything else, print one short line with this skill's version and its most recent change — the top entry of metadata.changelog above — e.g. install-kb-agent vX.Y — recent: <summary>. Then proceed.

Create a Cornelius-shaped knowledge-base agent powered by Claude Code, customized to a specific domain (community management, CS research, clinical research, legal analysis, personal KB, or custom), and compatible with Trinity for remote deployment, scheduling, and orchestration.

What you'll get:

  • A Brain Dependency Graph ontology (<agent>-graph.yaml) tuned to the domain
  • A 7-layer vault scaffold (signals → impressions → insights → frameworks → lenses → syntheses → indices)
  • The cornelius local-brain-search Python machinery cloned in — FAISS vector search, spreading activation, coherence engine
  • Domain-appropriate subagents (vault-manager + extractors + discovery + synthesis)
  • KB-core scheduled skills: /coherence-sweep, /compute-lifecycle, /detect-tensions, /refresh-index, /propagate-change
  • Domain-specific skills tailored to the preset (or blank if custom)
  • Onboarding tracker, Trinity dashboard, and all standard agent files

Built by Ability.ai. The agent this wizard generates is a specialization of Cornelius — the reference insight-harvester KB agent.


Background: Why a Structured Interview

Every KB agent shares the same skeleton. What differs across domains is how six slots get filled:

  1. Atomic unit — the smallest indivisible thing the agent captures
  2. Entity types — the taxonomy of first-class nouns beyond the atomic unit
  3. Edge types — how entities connect, with direction, mode, and decay
  4. Mode model — which entities are generative (prescriptive) vs reflective (descriptive)
  5. Trigger topology — edit-driven vs event-driven vs hybrid
  6. Lifecycle signals — observed behaviors that promote/demote entities

Read the full file on GitHub · 1,523 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 · 1,523 lines · 52 tokens per session scan D 9ddbf4b77deb

Subscribe to this mod's changes

install-kb-agent is a skill published in the GitHub repository Abilityai/abilities (11 stars, last pushed 14d ago), licensed MIT. It adds 52 tokens to every session and 18,175 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). 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

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens

babysit-pr

Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…

openai/codex · 114 tokens

imagegen

Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…

openai/codex · 113 tokens

agent-host-chat-contributions

Build and review cross-cutting agent-host chat behavior through lifecycle contributions. Use when adding turn lifecycle side effects, prompt or context injection, restored-history transformation, protocol-action observation, or when reviewing changes that add code to AgentSideEffects or AgentService.

microsoft/vscode · 56 tokens