sem is a Git-based semantic version control tool that compares changes to code entities such as functions, methods, and classes instead of individual lines. It helps developers and coding agents review changes, trace responsibility, and assess their impact across repositories. Catalogue add-ons provide agent integrations and workflows for operating sem.
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 skills add Ataraxy-Labs/sem --skill sem-code-reviewgit 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/sem-code-review)<a href="https://agentmods.dev/skills/ataraxy-labs/sem/sem-code-review"><img src="https://agentmods.dev/badge/skills/ataraxy-labs/sem/sem-code-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/ataraxy-labs/sem/sem-code-review"><img src="https://agentmods.dev/badge/skills/ataraxy-labs/sem/sem-code-review.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00039 | $0.00533 |
| Opus 5.5 | $0.00016 | $0.00213 |
| Sonnet 5.5 | $0.00008 | $0.00107 |
| Haiku 4.5 | $0.00004 | $0.00053 |
Grade A, and why
sem-code-review 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.
What it actually says
Code discovery and review with Sem
Use the existing terminal tool in the user's chosen repository. Check sem --version
first: this skill targets Ataraxy Sem 0.27.0, not GNU Parallel's sem executable.
If it is missing or incompatible, explain the prerequisite instead of installing
software or changing the user's tool configuration automatically.
For local-only operation, prefix each Sem invocation with
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1. These settings prevent Sem cloud access
and telemetry even if the user enabled them elsewhere. They are not an OS sandbox.
Choose the smallest query that answers the question (examples use parse_config):
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1 sem find parse_config --json
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1 sem find parse_config --callers --json
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1 sem find parse_config --context --budget 3000 --json
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1 sem diff --json
SEM_NO_NETWORK=1 SEM_NO_TELEMETRY=1 sem impact parse_config --tests --json
Several known names can share one definition query: sem find parse_config load_config --json.
For a requested commit range use sem diff BASE..HEAD --json, substituting the
actual refs. Do not invent a base branch or treat untracked files as part of the diff;
check the host's Git status tool when those matter.
Read bodies or surrounding source only when the task needs them. Disambiguate
duplicate names with --in for find or --file for impact. Static caller/test
results can be incomplete; an empty result is not proof that no caller or test
exists. Use ordinary text search and file reads for missing relationships,
configuration, unsupported syntax, or omitted context.
For review, report changed entities, affected callers, and unresolved questions
with source locations. Structure does not prove runtime correctness. Keep edits
and test execution within the user's request and the host's existing approval
flow. Do not run sem check merely to inspect a diff: it executes repository
compiler, linter and test commands. A review request does not authorize those
commands, Git configuration changes, commits, or a merge.
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 · 44 lines · 39 tokens per session scan A d63d4f034cd7
sem-code-review is a skill published in the GitHub repository Ataraxy-Labs/sem (3,413 stars, last pushed 2d ago), licensed Apache-2.0. It adds 39 tokens to every session and 533 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-14.
Other skills, from other repositories
inspect
Entity-level code review for Git. Scores changes by risk and groups them by logical dependency.
poly-and-release-workflow
Commit step lint/test/harness order.
commit
A commit candidate is the exact patch that will enter the commit. A coherent change has one task or issue as its reason for existing.
resolving-merge-conflicts
Use when you need to resolve an in-progress git merge/rebase conflict.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
otto-pr-review-loop
Run Polly and OCR on a PR until all findings settle.