kb-lint

kb-lint is a skill for Claude Code from SteveGJones/ai-first-sdlc-practices. It costs 64 tokens per session (3,400 once invoked), scanned A, original, MIT.

A health check for a project knowledge base, a collection of files that documents a project. It reports contradictions, outdated claims, unlinked files, missing concept pages, missing references, and data gaps.

In plain words
What is it for?
Use it to audit the consistency and coverage of a knowledge-base library, optionally limiting the check to matching files or failing on invalid metadata.
Why use it?
It reveals when project documentation has drifted apart or important information is missing.

Skill for Claude Code

Written for Claude Code: disable-model-invocation in frontmatter.

Runs only inside its plugin — its command needs a path that Claude Code sets for a plugin’s own hooks and for nothing else. Install the plugin, not this.

Part of the sdlc-knowledge-base plugin — 16 skills, 4 agents shipped together

Good fit Use it to audit the consistency and coverage of a knowledge-base library, optionally limiting the check to matching files or failing on invalid metadata.

Compare 6 skills from other repositories ↓
Install

Getting it into your agent

This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.

Claude Code
/plugin marketplace add SteveGJones/ai-first-sdlc-practices
Claude Code
/plugin install sdlc-knowledge-base

Made for: Claude Code.

Or install sdlc-knowledge-base, the plugin that ships this one along with the rest of its 16 skills, 4 agents.

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-lint

README.md
[![agentmods](https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-lint/github.svg)](https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-lint)
Your own site
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-lint"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-lint/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 kb-lint

Your own site · 80×15
<a href="https://agentmods.dev/skills/stevegjones/ai-first-sdlc-practices/kb-lint"><img src="https://agentmods.dev/badge/skills/stevegjones/ai-first-sdlc-practices/kb-lint.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 64 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,400 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.
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 $0.00064 $0.03400
Opus 5.5 $0.00026 $0.01360
Sonnet 5.5 $0.00013 $0.00680
Haiku 4.5 $0.00006 $0.00340

Measured 1mo ago against content hash 8ea91976c09b, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

kb-lint 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 1mo 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.

plugins/sdlc-knowledge-base/skills/kb-lint/SKILL.md · 355 lines

How it starts

The opening of the file, as written. The whole thing — 355 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Knowledge Base Lint

Periodic health-check for the project's knowledge base. This is the lint operation in the three-operations model (ingest / query / lint), adopted from Karpathy's LLM Wiki gist.

The staleness check that runs in environment validation catches one kind of drift (file changed since last index). Lint catches the other kinds: logical drift, orphan accumulation, missing concepts, contradictions, gaps. Both are needed.

Arguments

Optional --scope <pattern> to limit lint to a subset of library files. Default is the entire library.

Optional --strict-layer to fail with a non-zero exit when any library file has a missing or invalid layer: frontmatter field. Without this flag, layer violations are reported as warnings only in the Layer Compliance section.

Optional --strict-confidence to fail with a non-zero exit when any library file has a missing or invalid confidence: field. Without this flag, confidence violations are reported as warnings in the Layer Compliance section.

Optional --auto-fix to run the mechanical frontmatter fixer (kb_lint_fix.py) before lint. Auto-fix adds missing layer:, confidence:, and cross_references: fields with safe defaults, and creates stub frontmatter (with confidence: low, status: draft) for files that have no frontmatter at all. After fixing, the shelf-index is rebuilt before lint proceeds.

Examples:

  • --scope dora-*.md — lint only DORA-related files
  • --scope library/architecture/*.md — lint a sub-directory
  • --strict-layer — enforce layer compliance (used by this repo's CI)
  • --strict-layer --scope *.md — combine both
  • --strict-confidence — enforce confidence compliance
  • --auto-fix --strict-layer --strict-confidence — fix mechanics, then enforce both
  • (no argument) — lint everything, warnings only

Preflight

  • Verify the knowledge base is configured.
  • Verify the shelf-index is fresh: invoke kb-rebuild-indexes first if any library files are newer than the index. (The lint output is only meaningful against an up-to-date index.)
  • Verify there are at least 3 library files. Linting an empty or near-empty library is not useful.

Read the full file on GitHub · 355 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. 1mo ago First seen · 355 lines · 64 tokens per session scan A 8ea91976c09b

Subscribe to this mod's changes

kb-lint is a skill published in the GitHub repository SteveGJones/ai-first-sdlc-practices (41 stars, last pushed 15d ago), licensed MIT. It adds 64 tokens to every session and 3,400 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-03.