argot

Review changes against the patterns your repository has already accepted.
argot surfaces repository-grounded divergence; you decide what to accept.

argot.tmonier.com  ·  Documentation  ·  Evidence  ·  Research log

Start with an audit

argot audit needs no prior Argot fit or configuration. It fits a historical base in a temporary worktree, then evaluates the surviving base-to-HEAD net diff. Your working tree is left untouched. It is a review prompt—not a census of who wrote code, or proof that a finding is a defect.

# macOS / Linux
curl --proto '=https' --tlsv1.2 -LsSf https://github.com/get-tmonier/argot/releases/latest/download/argot-installer.sh | sh

cd your-repository
argot audit

Windows: powershell -c "irm https://github.com/get-tmonier/argot/releases/latest/download/argot-installer.ps1 | iex". The npm package is also available as npm install -g @tmonier/argot.

Audit needs usable Git history and supported source. It has no fixed runtime promise. Semantic analysis may download a local code-embedding model once; see Getting started for install, offline, and fit details.

If the audit gives you a useful lead, fit the current repository and score the changes you intend to review:

argot init
argot check

check reports configured findings on the selected changeset; a clean result does not prove the change correct or fully idiomatic. Read the Audit, Init and Fit, and Check guides for the exact contracts.

What it surfaces

argot is a probabilistic review guardrail, not a correctness oracle. Its current detector composition can surface a foreign dependency/API/idiom, a function that duplicates one already present, code placed away from its peers, an internal import that reverses a learned direction, or a test weakened, disabled, or deleted alongside the production change it covers. Repositories can also add their own versioned scripted rules.

Each finding carries repository evidence. Treat it as a prompt to inspect and make the human decision explicit—never as proof that the code is wrong.

Choose how to run it

The CLI is the complete, explicit changeset check. Other routes have narrower triggers and coverage; none provides a universal acceptance-time check.

Canonical setup and host details: Claude Code, other agents and MCP, and CI and pre-commit.

Evidence and limits

Current public measurements are detector-specific, not a product-wide accuracy or combined-brief claim. The approved claim manifest records:

• visible foreign-symbol fixtures: 595/605 across 22 corpora;
• layering fixtures: 264/272 across 25 corpora and 12 languages;
• test-integrity fixtures: 155/164 across 23 corpora and 12 languages.

Each number has a distinct corpus, denominator, and qualifier. The combined briefing/noise result, semantic aggregate, and ordinary-repository timing are not yet measured public claims. See the benchmark methodology and sources.

Argot ships adapters for 12 languages. The five tested release targets are macOS arm64/x64, Linux x64/arm64, and Windows x64. The local analysis path uses statistical, graph, scripted, and embedding evidence; no generative or opinion-forming model decides a finding.

Fit health matters. A repository with shallow, generated, vendored, or otherwise unsuitable history may not produce a useful model. Argot is also least reliable for an incorrect choice made entirely with familiar vocabulary, masked prose, and code outside the selected range. Read Limitations before relying on a specific detector.

Reproducible authored proof

This is an authored fixture, not a wild-case corpus. Its pinned command, version, receipts, checksums, regeneration procedure, and the visual’s non-byte-stable GIF qualification are documented in the proof receipt. The image is a reproducible companion to the auditable Markdown receipt.

Privacy and open source

Argot analyzes source, history, and findings locally. The individual local core is free, MIT-licensed open source, and requires no account or cloud service. Argot has no default telemetry and does not upload source code. It can still use network paths for a one-time local model download, update/version checks, release downloads, or an explicitly configured review/update/CI integration. Set ARGOT_OFFLINE=1 to prevent network use; semantic checks without a cached model are then skipped with a diagnostic while other checks continue.

Read the complete privacy and security boundary, security policy, and MIT license.

Contribute

Contributions are welcome. Start with CONTRIBUTING.md, then see the product strategy for the maintained decision record and research log for evidence.