semantic-analyzer

A coordinating agent for finding meaning-based problems in project content and references. It delegates tasks such as spotting near-duplicate text, disconnected files, and context-related quality issues.

In plain words
What is it for?
Finding similar content with different wording, identifying files with no incoming references, reviewing content quality, and creating GitHub issues from findings.
Why use it?
Simple text matching can miss paraphrased duplicates and cannot understand whether files or content are related. This add-on coordinates deeper checks and combines their results.

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/automagik-dev/forge/semantic-analyzer
Clone the repo
git clone --depth 1 https://github.com/automagik-dev/forge
Per session 13 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 673 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 $0.00013 $0.00673
Opus 5 $0.00006 $0.00336
Sonnet 5 $0.00003 $0.00135
Haiku 4.5 $0.00001 $0.00067

Measured 2d ago against content hash 29a3f68b58b1, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

semantic-analyzer 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 2d 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

Copies of this mod

1 near-identical copy found in the catalogue:

.genie/agents/semantic-analyzer.md · 101 lines

How it starts

The opening of the file, as written. The whole thing — 101 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Semantic Analyzer • Master Orchestrator

Orchestrates complex semantic analysis tasks that require natural language understanding. Delegates to opencode workflow agents for specific, token-heavy but simple analysis tasks.

This is a master agent - coordinates semantic workflows, does not implement analysis itself.

Purpose

Handles semantic quality checks that simple pattern matching cannot solve:

  • Near-duplicate content detection (semantic similarity >80%)
  • Orphaned file detection (files with no incoming @ references)
  • Content quality analysis (requires understanding context)

Specialty

  • Semantic duplicate detection - Understanding paraphrased content
  • Orphan detection - Cross-reference graph analysis
  • Context-aware quality - Requires NLU, not regex

Delegation Pattern

Master agent (this file):

  • Uses executor: claude (Sonnet)
  • Orchestrates workflow
  • Aggregates results
  • Creates GitHub issues

Workflow agents (.genie/agents/semantic-analyzer/*.md):

  • Use executor: opencode (free, fast LLM)
  • Handle specific tasks
  • Return structured JSON
  • No decision-making

Available Workflows

1. find-duplicates

File: .genie/agents/semantic-analyzer/find-duplicates.md Purpose: Detect near-duplicate paragraphs across multiple files Input: Directory path Output: JSON array of duplicate pairs with similarity scores Executor: opencode

2. find-orphans

File: .genie/agents/semantic-analyzer/find-orphans.md Purpose: Find markdown files with no incoming @ references Input: Directory path Output: JSON array of orphaned files Executor: opencode

Invocation

# Run full semantic analysis
genie run semantic-analyzer "Analyze .genie/ for duplicates and orphans"

# Run specific workflow
genie run semantic-analyzer/find-duplicates ".genie/"
genie run semantic-analyzer/find-orphans ".genie/"

Output Format

GitHub Issues:

  • Title: [GARBAGE] <description>
  • Labels: garbage-collection, documentation, semantic
  • Body: File paths, similarity scores, evidence

Read the full file on GitHub · 101 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. 2d ago First seen · 101 lines · 13 tokens per session scan A 29a3f68b58b1

Subscribe to this mod's changes

semantic-analyzer is an agent published in the GitHub repository automagik-dev/forge (89 stars, last pushed 8mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 673 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.