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.
npx agentmods add skills/ataraxy-labs/sem/agent-skillnpx skills add Ataraxy-Labs/sem --skill agent-skillgit clone --depth 1 https://github.com/Ataraxy-Labs/semWrote 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.
[](https://agentmods.dev/skills/ataraxy-labs/sem/agent-skill)<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>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.
| Model | Per session | Once 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 |
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.
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.
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.
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.
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.
- 4d ago First seen · 158 lines · 112 tokens per session scan A 30b9aec0543d
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.
Other skills, from other repositories
self-repair-pipeline
Runs the full entry point self-repair pipeline. Detects entry points in Ariadne packages or external codebases, triages false positives via sub-agents, plans fixes for each issue group with competing proposals and multi-angle review, and creates backlog tasks.
mcp-headless-test
Run live tests of the Ariadne MCP server using Claude Code in headless mode. Tests tool discovery, invocation, and filtering. Use when validating MCP server changes or checking integration with Claude Code.
mcp-analytics
Check Ariadne MCP tool usage analytics — session counts, tool call stats, durations, and error rates.
release
Prepare a new release of Ariadne packages. Creates changesets, verifies build/tests, and drafts the PR to main.
N3MO Code Intelligence
Use N3MO's MCP tools to search symbols, find dependencies, and check blast radius. This skill enforces using MCP over CLI commands.
inspect
Entity-level code review for Git. Scores changes by risk and groups them by logical dependency.