aget-check-kb

aget-check-kb is a skill for Claude Code from aget-framework/template-advisor-aget. It costs 38 tokens per session (846 once invoked), scanned A, a copy of aget-check-kb, Apache-2.0.

A health checker for a knowledge base, meaning the organised files an agent uses as reference material. It checks structure, required metadata, and whether documents are out of date.

In plain words
What is it for?
Auditing the knowledge directory, counting and organising its Markdown files, checking required documentation, and finding content older than set age thresholds.
Why use it?
It reveals missing files, organisation problems, invalid frontmatter, and stale documentation, then reports an OK, warning, or critical status.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

Good fit Auditing the knowledge directory, counting and organising its Markdown files, checking required documentation, and finding content older than set age thresholds.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/aget-framework/template-advisor-aget/aget-check-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 aget-framework/template-advisor-aget --skill aget-check-kb
Clone the repo
git clone --depth 1 https://github.com/aget-framework/template-advisor-aget

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 aget-check-kb

README.md
[![agentmods](https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-check-kb/github.svg)](https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-check-kb)
Your own site
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-check-kb"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-check-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 aget-check-kb

Your own site · 80×15
<a href="https://agentmods.dev/skills/aget-framework/template-advisor-aget/aget-check-kb"><img src="https://agentmods.dev/badge/skills/aget-framework/template-advisor-aget/aget-check-kb.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 38 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 846 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 100% copy Near-identical to another mod 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 $0.00038 $0.00846
Opus 5 $0.00019 $0.00423
Sonnet 5 $0.00008 $0.00169
Haiku 4.5 $0.00004 $0.00085

Measured 12d ago against content hash 59d90b101227, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

aget-check-kb 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 12d 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.

Origin

This is a copy

100% identical to aget-check-kb — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.claude/skills/aget-check-kb/SKILL.md · 138 lines

How it starts

The opening of the file, as written. The whole thing — 138 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/aget-check-kb

Validate the health of the knowledge/ directory by checking structure, file organization, and content freshness.

Purpose

Provide self-diagnostic capability for AGET agents to assess their knowledge base health. Identifies structural issues, missing documentation, and stale content.

Execution

When invoked, perform these checks:

1. Structure Check

# Check if knowledge/ exists
test -d knowledge && echo "exists" || echo "missing"

# List subdirectories
find knowledge -type d -mindepth 1 -maxdepth 1

# Check for README
test -f knowledge/README.md && echo "yes" || echo "no"

2. File Inventory

# Count markdown files
find knowledge -type f -name "*.md" | wc -l

# Count by subdirectory
for dir in knowledge/*/; do
  echo "$dir: $(find "$dir" -type f -name "*.md" | wc -l)"
done

3. Staleness Check

# Find files not modified in 90+ days
find knowledge -type f -name "*.md" -mtime +90 | wc -l

# Find files not modified in 180+ days
find knowledge -type f -name "*.md" -mtime +180 | wc -l

4. Disk Usage

du -sh knowledge

Thresholds

Metric OK WARN CRITICAL
KB exists yes - no
README exists yes no -
Staleness (90+ days) <25% 25-50% >50%
Staleness (180+ days) <10% 10-25% >25%

Note: Research AGET baseline (2026-02-08): 14 files, 96K.

Output Format

=== /aget-check-kb ===

Directory: knowledge/

Structure:
  KB exists:     [yes/no]
  README:        [yes/no]
  Subdirectories: [list]

File Counts:
  Total files:   [count]
  By directory:
    [dir]: [count]
    ...

Staleness:
  >90 days:  [count] ([%])
  >180 days: [count] ([%])

Disk Usage: [size]

Health Status: [OK | WARN | CRITICAL]
Alerts:
  [list any threshold violations]

Health Status Logic

IF kb_missing:
  CRITICAL
ELIF stale_180 > 25% OR stale_90 > 50%:
  CRITICAL
ELIF readme_missing OR stale_180 > 10% OR stale_90 > 25%:
  WARN
ELSE:
  OK

Read the full file on GitHub · 138 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. 12d ago First seen · 138 lines · 38 tokens per session scan A 59d90b101227

Subscribe to this mod's changes

aget-check-kb is a skill published in the GitHub repository aget-framework/template-advisor-aget (2 stars, last pushed 2d ago), licensed Apache-2.0. It adds 38 tokens to every session and 846 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to aget-check-kb, differing in 0 lines, and is treated as a copy.

Related

Other skills, from other repositories

docutranslate

Use when translating documents locally via LLM — PDF, Word, Excel, Markdown, SRT subtitles with format preservation. DocuTranslate: LLM-powered multi-format local file translation tool with MCP server support.

znlgis/opengis-skills · 47 tokens

add-docs-page

Scaffold a new MkDocs documentation page and wire it into the navigation. Use when asked to "add a docs page", "add a guide", or "document" a feature in the site.

gpauloski/python-template · 45 tokens

doc-coauthoring

Guide users through a structured workflow for co-authoring documentation. Use when user wants to write documentation, proposals, technical specs, decision docs, or similar structured content. This workflow helps users efficiently transfer context, refine content through iteration, and verify the doc works for readers.…

Zandereins/schliff · 77 tokens

active-directory-attacks

Provide comprehensive techniques for attacking Microsoft Active Directory environments. Covers reconnaissance, credential harvesting, Kerberos attacks, lateral movement, privilege escalation, and doma.

ranbot-ai/awesome-skills · 33 tokens

officecli-data-dashboard

Use this skill to build a multi-element Excel dashboard — Dashboard sheet on open, multiple formula-driven KPI cards, multiple charts, sparklines, and conditional formatting — from CSV or tabular input. Trigger on: 'dashboard', 'KPI dashboard', 'analytics dashboard', 'executive dashboard', 'metrics dashboard', 'CSV to…

iOfficeAI/OfficeCLI · 157 tokens

gws-sheets

Google Sheets: Read and write spreadsheets.

googleworkspace/cli · 13 tokens