deduplicate

A duplicate-finding tool for Semantica knowledge graphs. It uses fuzzy matching, meaning it can compare similar-looking names or values rather than requiring exact matches.

In plain words
What is it for?
It detects duplicate entities, groups similar records, identifies repeated relationships, and suggests representative records for merging.
Why use it?
It helps find repeated entities and relationships that can make a knowledge graph inconsistent or harder to use.

Skill for Claude CodeCodex

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 skills/semantica-agi/semantica/deduplicate
Any agent
npx skills add semantica-agi/semantica --skill deduplicate
Clone the repo
git clone --depth 1 https://github.com/semantica-agi/semantica

Made for: Claude Code, Codex.

Per session 29 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 242 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 $0.00029 $0.00242
Opus 5 $0.00015 $0.00121
Sonnet 5 $0.00006 $0.00048
Haiku 4.5 $0.00003 $0.00024

Measured yesterday against content hash 77f908ee2fe8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deduplicate 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.

plugins/skills/deduplicate/SKILL.md · 42 lines

What it actually says

/semantica:deduplicate

Remove duplicates from the knowledge graph. Usage: /semantica:deduplicate <strategy> [args]

$ARGUMENTS = deduplication strategy + optional entity or threshold.


entities [--threshold <score>] [--field <name>]

Detect duplicate entities and group them by similarity.

from semantica.deduplication import DuplicateDetector

finder = DuplicateDetector()
candidates = finder.detect_duplicates(entities, threshold=threshold)
groups = finder.detect_duplicate_groups(entities, threshold=threshold)

Output: duplicate candidate list, duplicate groups, and representative merge recommendations.


relations [--similarity <score>]

Detect duplicate relationships and normalize edge representations.

from semantica.deduplication import DuplicateDetector

finder = DuplicateDetector()
relations = finder.detect_duplicates(relation_list, threshold=similarity)

Result: duplicate relation candidates, normalized relationship groups, and cleanup summary.

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 · 42 lines · 29 tokens per session scan A 77f908ee2fe8

Subscribe to this mod's changes

deduplicate is a skill published in the GitHub repository semantica-agi/semantica (11,359 stars, last pushed yesterday), licensed MIT. It adds 29 tokens to every session and 242 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.

Related

Other skills, from other repositories