sem

sem is a skill for Claude Code, Codex from Ataraxy-Labs/sem. It costs 112 tokens per session (1,331 once invoked), scanned A, original, Apache-2.0.

A Git extension that shows changes to whole functions, classes, and methods instead of only changed lines. It also provides related dependency and history information.

In plain words
What is it for?
Use it to review commits and pull requests, compare files or revisions, find who last changed a function or class, and trace how code evolved.
Why use it?
Line-by-line diffs can hide which code element changed and what it may affect. This gives a clearer view of changes and their possible impact in any Git repository.

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/ataraxy-labs/sem/agent-skill
Any agent
npx skills add Ataraxy-Labs/sem --skill agent-skill
Clone the repo
git clone --depth 1 https://github.com/Ataraxy-Labs/sem

Made for: Claude Code, Codex.

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 sem

README.md
[![agentmods](https://agentmods.dev/badge/skills/ataraxy-labs/sem/agent-skill.svg)](https://agentmods.dev/skills/ataraxy-labs/sem/agent-skill)
Your own site
<a href="https://agentmods.dev/skills/ataraxy-labs/sem/agent-skill"><img src="https://agentmods.dev/badge/skills/ataraxy-labs/sem/agent-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 112 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,331 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 $0.00112 $0.01331
Opus 5 $0.00056 $0.00665
Sonnet 5 $0.00022 $0.00266
Haiku 4.5 $0.00011 $0.00133

Measured 4d ago against content hash 30b9aec0543d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sem 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 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (badge/sem-activity.py, badge/sem-live.py, badge/statusline-sem.py, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

agent-skill/SKILL.md · 158 lines

How it starts

The opening of the file, as written. The whole thing — 158 lines — stays where its author put it; the contents beside it link to each section on GitHub.

sem — Semantic Version Control

sem extends Git with entity-level operations. Instead of "lines 43-51 changed", it tells you "function validateToken was modified in src/auth.ts". It parses 30+ languages via tree-sitter and works in any Git repo with no setup.

When to reach for sem

  • User asks "what changed in this commit / PR / branch?"
  • User wants to know what will break if they change a function
  • User asks who last touched a function or class
  • User wants to trace how a function evolved over time
  • You need structured, token-efficient code context for an LLM subtask
  • You're doing a code review and want entity-level signal, not line noise

Commands

sem diff — what changed?

sem diff                          # working tree changes
sem diff --staged                 # staged only
sem diff --commit abc1234         # specific commit
sem diff --from HEAD~5 --to HEAD  # commit range
sem diff file1.ts file2.ts        # compare two files (no git needed)
sem diff --format json            # structured output for further processing
sem diff --format markdown        # for PRs / reports
sem diff -v                       # verbose: word-level inline diffs
sem diff --file-exts .py .rs      # filter by extension

Change types: added, modified (structural vs cosmetic), deleted, renamed/moved.

sem impact — blast radius

sem impact validateToken          # everything affected if this changes
sem impact validateToken --deps   # direct dependencies only
sem impact validateToken --dependents  # direct dependents only
sem impact validateToken --tests  # affected tests only
sem impact validateToken --json
sem impact validateToken --file src/auth.ts  # disambiguate

Use this before refactoring or deleting a function to understand scope.

sem blame — who last touched this?

sem blame src/auth.ts             # entity-level blame for a file
sem blame src/auth.ts --json

Unlike git blame, this shows who last modified each function, not each line.

Read the full file on GitHub · 158 lines

Files

What ships with it

7 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

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. 4d ago First seen · 158 lines · 112 tokens per session scan A 30b9aec0543d

Subscribe to this mod's changes

sem is a skill published in the GitHub repository Ataraxy-Labs/sem (3,328 stars, last pushed 2d ago), licensed Apache-2.0. It adds 112 tokens to every session and 1,331 once invoked, about $0.0006 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.