tag-suggester

tag-suggester is an agent for coding agents from datacore-one/datacore. It costs 48 tokens per session (1,990 once invoked), scanned A, original, MIT.

An agent that reads content and suggests tags from an existing tag registry. It can combine those suggestions with tags supplied by the user.

In plain words
What is it for?
Use it when processing research, conversations, work sessions, or inbox items that need organised labels.
Why use it?
It removes the repetitive work of choosing and formatting consistent tags for stored content.

Agent

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 agents/datacore-one/datacore/tag-suggester
Clone the repo
git clone --depth 1 https://github.com/datacore-one/datacore

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 tag-suggester

README.md
[![agentmods](https://agentmods.dev/badge/agents/datacore-one/datacore/tag-suggester.svg)](https://agentmods.dev/agents/datacore-one/datacore/tag-suggester)
Your own site
<a href="https://agentmods.dev/agents/datacore-one/datacore/tag-suggester"><img src="https://agentmods.dev/badge/agents/datacore-one/datacore/tag-suggester.svg" alt="Measured on agentmods" height="20"></a>
Per session 48 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,990 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 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 $0.00048 $0.01990
Opus 5 $0.00024 $0.00995
Sonnet 5 $0.00010 $0.00398
Haiku 4.5 $0.00005 $0.00199

Measured yesterday against content hash 4d1795fbd755, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

tag-suggester 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 yesterday.

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.

.datacore/agents/tag-suggester.md · 285 lines

How it starts

The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tag Suggester Agent

Engram Injection

Before starting work, load relevant learned patterns:

  1. Preferred: Call plur_admin MCP tool with action = "plur_inject_hybrid", prompt = your task description, scope = agent:tag-suggester
  2. Fallback: If MCP is unavailable, read .datacore/state/agent-engrams/tag-suggester.md for compiled engrams

Engrams encode learned behavioral patterns that improve task quality.

Agent Context

When to Reference DIP-0014

Always reference when:

  • Suggesting tags for content
  • Validating tags against registry
  • Formatting inline tag strings
  • Merging existing with suggested tags

Key decisions this DIP informs:

  • Tag format: inline #tag1, #tag2 at end
  • Kebab-case normalization
  • Registry lookup order (system → space)
  • Never use tags: [array] in frontmatter

Quick Reference

Question Answer
Where is system registry? .datacore/tags.yaml
Where is space registry? [space]/.datacore/tags.yaml
Tag format? #tag1, #tag2, #tag3 inline
Who calls me? Research, conversation, session-learning, inbox agents

Related DIPs

Related Agents

Agent Relationship
knowledge-extractor Calls me for zettel and literature note tags
session-learning Calls me for new zettels
gtd-inbox-processor Calls me for task tags

Integration Points

  • DIP-0014 - Follows tag taxonomy specification
  • tag_utils.py - Uses for registry loading
  • Registry files - Validates against .datacore/tags.yaml

Purpose

AI-powered tag suggestion for content. Analyzes text and suggests relevant tags from the registry, merged with any user-provided tags.

Called by: knowledge-extractor, session-learning, gtd-inbox-processor, CRM agents

Input

  • content: Text to analyze for tag suggestions
  • context: Type of content (zettel, literature-note, task, contact, journal)
  • existing_tags: Optional list of already-assigned tags
  • space: Optional space name for space-specific tags
  • limit: Maximum suggestions (default: 5)

Read the full file on GitHub · 285 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. yesterday First seen · 285 lines · 48 tokens per session scan A 4d1795fbd755

Subscribe to this mod's changes

tag-suggester is an agent published in the GitHub repository datacore-one/datacore (4 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 1,990 once invoked, about $0.0002 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 2026-09-03.