agentspec: Skill for Claude Code

.claude/skills/kb-build/SKILL.md

kb-build is a skill for Claude Code from luanmorenommaciel/agentspec. It costs 173 tokens per session (2,602 once invoked), scanned A, original, MIT.

A process for building a knowledge base whose claims are checked against sources and reviewed for factual errors before use by other agents.

In plain words
What is it for?
Use it to research a subject, document verified findings, and create source-cited reference material.
Why use it?
It reduces the risk that unsupported information spreads from a shared reference into many agent responses or workflows.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: mentions subagents.

This is luanmorenommaciel/agentspec's own configuration. It tells Claude Code how to work on agentspec itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything agentspec configures →

Reuse

Borrowing it

Nothing to install: this file belongs to luanmorenommaciel/agentspec. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/luanmorenommaciel/agentspec/main/.claude/skills/kb-build/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/luanmorenommaciel/agentspec

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-build

README.md
[![agentmods](https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/kb-build.svg)](https://agentmods.dev/skills/luanmorenommaciel/agentspec/kb-build)
Your own site
<a href="https://agentmods.dev/skills/luanmorenommaciel/agentspec/kb-build"><img src="https://agentmods.dev/badge/skills/luanmorenommaciel/agentspec/kb-build.svg" alt="Measured on agentmods" height="20"></a>
Per session 173 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,602 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
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 $0.00173 $0.02602
Opus 5 $0.00086 $0.01301
Sonnet 5 $0.00035 $0.00520
Haiku 4.5 $0.00017 $0.00260

Measured 7d ago against content hash 208be56bf9d8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

kb-build 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 7d 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.

.claude/skills/kb-build/SKILL.md · 171 lines

How it starts

The opening of the file, as written. The whole thing — 171 lines — stays where its author put it; the contents beside it link to each section on GitHub.

KB Build — high-assurance, source-verified KB creation

Build a knowledge base where every claim is source-cited and adversarially verified before it lands. This skill serves two purposes: it produces the KB, and its body documents the process — read it as the SOP for how validated knowledge enters the repository.

A KB is a component whose single responsibility is to be a faithful knowledge-bearer. A foundational KB is consulted by many agents, so one unverified "standard" propagates into all of them. Faithfulness is therefore non-negotiable, and the verification bar is intrinsic to the kind of claim — a notation or standard claim demands an authoritative source — regardless of how many readers the KB will have. The distilled reasoning lives in references/lessons.md.

The two modes of /create-kb

The create-kb command is the single entrypoint for KB creation; this skill is the capability behind its --validated mode. The default mode is a direct, single-pass kb-architect run relying on the agent's own validation. Pick by stakes:

--validated (this skill) Default (light)
Foundational or high-stakes domain Quick, low-stakes domain
Every claim cited and independently fact-checked kb-architect's own validation suffices
Research + adversarial verification + fact-check gate Single pass, no separate verification layer
Worth more tokens for assurance Token-light

The skill can also be invoked directly for advanced use (custom research scope, partial reruns) — the entrypoint is a convenience, not a wall.

Scope fence

KBs hold technical domain knowledge for grounding agents: concepts, patterns, specs, quick references. Two things never belong in a KB:

  • Architecture decisions — record them as ADRs in the repository's decision log; the KB may cite a decision, never host it.
  • Meeting notes — they belong in the project's notes; distill any durable technical knowledge out of them (with sources) before it enters a KB.

Read the full file on GitHub · 171 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 7d ago First seen · 171 lines · 173 tokens per session scan A 208be56bf9d8

Subscribe to this mod's changes

kb-build is a skill published in the GitHub repository luanmorenommaciel/agentspec (246 stars, last pushed today), licensed MIT. It adds 173 tokens to every session and 2,602 once invoked, about $0.0009 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 2026-09-01.

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

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens

chronicle

Analyze Copilot session history for standup reports, usage tips, session search, and session reindexing. Use when the user asks for a standup, daily summary, usage tips, workflow recommendations, wants to search or find past sessions by keyword/file/PR, wants to reindex their session store, or asks about deleting…

microsoft/vscode · 72 tokens