auto-tag

auto-tag is a skill for Claude Code from DavidROliverBA/ArchitectKB. It costs 13 tokens per session (1,327 once invoked), scanned A, original, MIT.

A command for adding tags to notes that do not have tags by analysing their content and type. It can process the whole vault or a selected path, preview changes, filter by note type, and limit the number of notes.

In plain words
What is it for?
Use it to tag all untagged notes or a chosen folder, run a dry preview, process only a particular note type, or cap a batch by size.
Why use it?
It reduces the work of sorting unlabelled notes and makes them easier to find later.

Skill for Claude Code

Written for Claude Code: context: fork in frontmatter. Also seen: model in frontmatter; mentions subagents.

Good fit Use it to tag all untagged notes or a chosen folder, run a dry preview, process only a particular note type, or cap a batch by size.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/davidroliverba/architectkb/auto-tag
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 DavidROliverBA/ArchitectKB --skill auto-tag
Clone the repo
git clone --depth 1 https://github.com/DavidROliverBA/ArchitectKB

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 auto-tag

README.md
[![agentmods](https://agentmods.dev/badge/skills/davidroliverba/architectkb/auto-tag/github.svg)](https://agentmods.dev/skills/davidroliverba/architectkb/auto-tag)
Your own site
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/auto-tag"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/auto-tag/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 auto-tag

Your own site · 80×15
<a href="https://agentmods.dev/skills/davidroliverba/architectkb/auto-tag"><img src="https://agentmods.dev/badge/skills/davidroliverba/architectkb/auto-tag.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 13 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,327 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 $0.00013 $0.01327
Opus 5 $0.00006 $0.00664
Sonnet 5 $0.00003 $0.00265
Haiku 4.5 $0.00001 $0.00133

Measured 9d ago against content hash b464b1d00f64, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

auto-tag 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 9d 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/auto-tag/SKILL.md · 167 lines

How it starts

The opening of the file, as written. The whole thing — 167 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/auto-tag

Batch auto-tag notes that have empty or missing tags by analysing their content and type. Addresses the 61% empty tag rate in the vault.

Usage

/auto-tag                    # Process all untagged notes
/auto-tag <path>             # Process specific file or folder
/auto-tag --dry-run          # Preview changes without applying
/auto-tag --type Meeting     # Only process untagged notes of a specific type
/auto-tag --limit 50         # Process at most 50 notes

Instructions

Phase 1: Find Untagged Notes

Use Grep and Glob to find notes with empty tags:

# Find files with empty tags arrays
Grep for "tags: \[\]" in *.md files (exclude Templates/, .obsidian/, .claude/, Archive/)

# Also find files with no tags field at all
# Notes with tags containing only template variables

Filter results:

  • Exclude Templates/, .obsidian/, .claude/, Archive/, Attachments/
  • If --type specified, filter by frontmatter type field
  • If <path> specified, scope to that path
  • Sort by type for batch efficiency

Phase 2: Analyse and Tag (Parallel)

Launch parallel Haiku sub-agents, batching 20 notes per agent:

For each note, the agent should:

  1. Read frontmatter — extract type, title, project, status
  2. Read body content — first 500 words
  3. Determine tags using these rules:
Tag Selection Rules

By note type (always apply):

Type Auto-tags
ADR type/adr, activity/architecture
Meeting (infer from title/content)
Task (infer project from project: field)
Project activity/delivery + self-referencing project/ tag
System type/system
Incubator activity/research
Research activity/research
Concept (infer from content)
Pattern (infer from content)
Email (infer from content)
Reference (infer from referenceType and content)
Trip (no tags needed — skip)
Daily daily

By content analysis (keyword matching):

Read the full file on GitHub · 167 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. 9d ago First seen · 167 lines · 13 tokens per session scan A b464b1d00f64

Subscribe to this mod's changes

auto-tag is a skill published in the GitHub repository DavidROliverBA/ArchitectKB (52 stars, last pushed 6mo ago), licensed MIT. It adds 13 tokens to every session and 1,327 once invoked, about $0.0001 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 2026-08-30.