Argot Repository Style Analyzer
Learn unwritten conventions from Git history and flag changes that diverge from the repository.
- Source repo
- get-tmonier/argot
- Stars
- ★ 49
- Last updated
- 2mo ago
- License
- MIT
- Primary language
- Rust
- FA score
- 78/100 · Good
At a glance
- How it runs
- Works with
- Universal · cross-platformClaude Code
- Cost
- Free, no paid service needed
- Setup effort
- Low · running in minutes
- You'll need
- Typical use
- A maintainer reviewing AI-generated pull requests wants to catch dependencies, calls, or constructions that compile but have no precedent in the repository.
- Not a fit if
- Teams that need proof of defects, not probabilistic review prompts
- Repositories with shallow, generated, or vendored Git history
- Teams needing languages or platforms beyond the 12 adapters and five tested targets
- Source review
- 78/100 · Good
What does this agent do, and when should you use it?
Argot is an MIT-licensed Rust static binary that fits a statistical baseline from a repository's own Git history and evaluates selected changes against it. Its interfaces include the audit, init, check, and status CLI commands, plus skills, read-only MCP tools, a Claude Code plugin, pre-commit hooks, and a GitHub Action. It can surface unfamiliar dependencies and calls, foreign token patterns, duplicated functions, misplaced code, reversed architectural dependencies, weakened tests, and rule tampering. Findings include repository evidence and are intended as prompts for human review, not proof of a defect or a correctness verdict. Fitting and analysis can run locally without an account or cloud service, although useful results require suitable repository history and supported source code.
For an initial assessment, argot audit fits a historical baseline in a temporary worktree and evaluates the surviving base-to-HEAD net diff while leaving the working tree untouched. For continuing use, argot init creates argot.toml and a .argot/ fit snapshot; after those files are reviewed and committed, argot check scores the intended changeset, while argot status recommends a refresh when accepted source, function, or layout surfaces have materially changed. Built-in rules produce voice, semantic, architecture, integrity, and governance findings. Repositories can add rules through a TOML manifest and sandboxed Rhai script under .argot/rules/. The CLI performs the complete explicit check; MCP exposes read-only context, hunk, and complete-changeset tools; pre-commit checks staged supported files; and the GitHub Action scores a configured ref or range. The optional Claude Code pre-write hook checks only whether Write, Edit, or MultiEdit introduces a foreign import, and it asks rather than blocks.
- A maintainer reviewing AI-generated pull requests wants to catch dependencies, calls, or constructions that compile but have no precedent in the repository.
- A large codebase team uses
redundantandmisplacedbefore merging a new function to find an existing equivalent or a more historically appropriate module area. - An architecture owner checks whether a new internal import reverses the dependency direction learned from the repository.
- A test owner reviews production changes for deleted or disabled tests, gutted test bodies, and assertions that were removed, tautologized, or loosened.
- A team that wants reproducible local and CI review commits
argot.tomland.argot/so both environments read the same learned baseline. - A repository with project-specific governance requirements adds TOML and sandboxed Rhai rules and detects attempts to weaken locked rules.
How do you install or deploy this agent?
On macOS or Linux, run curl --proto '=https' --tlsv1.2 -LsSf https://github.com/get-tmonier/argot/releases/latest/download/argot-installer.sh | sh. On Windows, run powershell -c "irm https://github.com/get-tmonier/argot/releases/latest/download/argot-installer.ps1 | iex". The npm alternative is npm install -g @tmonier/argot. Tested release targets are macOS arm64/x64, Linux x64/arm64, and Windows x64. No account or API credential is required, and analysis can run offline. The first invocation must be made inside a repository with usable Git history and supported source code.
How do you use this agent?
For a trial, run cd your-repository followed by argot audit. If the audit produces useful leads, run argot init and then argot check. Review and commit the generated argot.toml and .argot/ snapshot, merge that snapshot into the branch future pull requests will target, and only then add CI in a separate change. CI reads the snapshot from the base branch and never fits a model. Later, use argot status to determine whether a local fit-and-commit refresh is warranted. Set ARGOT_OFFLINE=1 when network access must be prevented; this does not remove analytical functionality.
What are this agent's strengths and limitations?
- The baseline comes from the target repository's history rather than generic style rules or a second generative model, and every finding carries repository evidence.
- Core analysis is local: the embedding model is compiled into the binary, no account or cloud service is required, source code is not uploaded, and telemetry is off by default.
- One system covers repository voice, semantic duplication, code placement, architectural layering, test integrity, and rule governance, with extensibility through sandboxed Rhai rules.
- CLI, MCP, Claude Code, pre-commit, and GitHub Actions routes support different workflows, while local checks and CI can share one committed baseline.
- Published evidence reports detector-specific catch rates, corpus sizes, qualifiers, and measured noise instead of presenting one unsupported aggregate accuracy claim.
- It depends on sufficiently deep and suitable Git history; shallow, generated, vendored, or otherwise unsuitable history may not yield a useful model.
- Initial adoption requires a local fit, human review, and committing a
.argot/snapshot that is typically a few megabytes to a few tens of megabytes; its pull request must land before the CI workflow change. - Findings are probabilistic review prompts rather than proof of defects, and errors expressed entirely through familiar vocabulary or located outside the selected range may escape detection.
- Coverage differs by route: the Claude Code hook checks only foreign imports, MCP depends on client tool selection, and the GitHub Action's
fail-on-hitssetting defaults tofalse. - Public measurements are detector-specific; the project does not yet publish a product-wide accuracy figure, combined-briefing result, or ordinary-repository runtime claim.
- The documented scope is limited to 12 language adapters and five tested release targets; the source provides no assurance for other languages or platforms.
How does this agent compare with similar options?
A type checker asks whether code satisfies its type constraints; Argot asks whether a change resembles the code, layout, and dependency direction established by that repository. Unlike sending the code to a second LLM for an opinion, Argot derives findings from local statistical, graph, scripted, and embedding evidence, with no generative or opinion-forming model deciding the result. The tradeoff is that it remains a repository-specific review guardrail, not a general correctness oracle.
Key facts side by side with the most closely related agents.
| Agent | Source review | Form / cost | Stars | Updated | Language | Full support on |
|---|---|---|---|---|---|---|
| Argot Repository Style Analyzer This agent | 78 · Good | CLIFree | ★ 49 | 2mo ago | Rust | Claude Code |
| Gortex Code Intelligence | 73 · Some gaps | CLIFree | ★ 2k | today | Go | Codex · Claude Code · OpenAI API · Claude API |
| Aura Code Audit Trail | 50 · Major gaps | CLIFree | ★ 49 | 27d ago | Rust | Codex · Claude Code |
| Concord MCP | 75 · Good | — | ★ 1k | 3d ago | TypeScript | Codex · Claude Code |
How does FollowAgents rate this agent?
Why each dimension lost points
The sources state that analysis runs locally with no telemetry or source upload, and identify separate network paths such as updates, installation, and configured CI; ARGOT_OFFLINE=1 can block update requests. Custom Rhai rules have no I/O and documented resource and per-file time limits, while dependency review and release checks are described. Deductions: installation and updates still involve network activity, and this sample does not show per-operation confirmation, detailed sensitive-data handling, or a complete rollback process. Attribution appears in plugin metadata and the security policy, but publisher identity is unverified.
The README, CLI entry point, and skills generally agree on local fit snapshots, checking workflows, and treating findings as review prompts. Dependency choices and some risks are explained, and error handling uses contextual messages and stderr. Deductions: the supplied evidence does not include the full dependency lock state or all user-facing error text, and does not allow checking every integration path for consistency.
The README and skills address developers and coding agents across local changes, PR review, CI, setup, and snapshot refresh, with explicit distinctions among triggers. They describe probabilistic behavior, prerequisites, offline use, and why a clean result does not prove correctness. Deduction: platform support is only partially enumerated in this sample, which lacks a complete compatibility matrix.
The README, AGENTS.md, and skills organize onboarding, rules, workflows, and limitations, with command examples, decision tables, and practical instructions; the MIT license is present. Deductions: version information is mainly exposed through badges and plugin/Cargo metadata, while the changelog body is absent from the sample; maintenance is single-person and response timelines are best-effort.
The tool offers machine-readable and several rendered output formats, stable finding identifiers, evidence trails, and multiple detector types, with public measurements separated by detector. Its additional value is repository-history-based evidence for code review. Deductions: value depends on suitable Git history and fit quality; results are probabilistic prompts rather than proof of correctness, and no fixed runtime is promised.
The README ties measurements to individual detectors, sample sizes, and qualifications, separates measured from unmeasured claims, and labels the demo as an authored fixture with a receipt. Deductions: the receipt, research records, and benchmark implementation are not included in this packet, and repeated product claims across files do not constitute independent corroboration.
- Treat findings as review leads, not defect verdicts; a clean result does not prove correctness or full conformity with repository conventions.
- Result quality depends on Git history, supported source, and fit-snapshot health; review scope during initial fitting and refresh as documented.
Maintain this project? Add the FARS badge to your README
[](https://followagents.com/en/agents/argot)<a href="https://followagents.com/en/agents/argot"><img src="https://followagents.com/badge/argot.svg" alt="FARS review"></a>Recent releases
Latest entries from the project's GitHub Releases. Notes are quoted from upstream as written, not rewritten or tested by FollowAgents.
-
Release notes excerpt
Install argot 0.2.129 Install prebuilt binaries via shell script ```sh curl --proto '=https' --tlsv1.2 -LsSf https://github.com/get-tmonier/argot/releases/download/v0.2.129/argot-installer.sh | sh ``` Install prebuilt binaries via powershell script ```sh powershell -ExecutionPolicy Bypass -c "irm https://github.com/get-tmonier/argot/releases/download/v0.2.129/argot-installer.ps1 | iex" ``` Install prebuilt binaries into your npm project ```sh npm install @tmonier/[email protected] ``` Download argot 0.2.129 | File | Platform | Checksum | …View on GitHub ↗ -
Release notes excerpt
Install argot 0.2.128 Install prebuilt binaries via shell script ```sh curl --proto '=https' --tlsv1.2 -LsSf https://github.com/get-tmonier/argot/releases/download/v0.2.128/argot-installer.sh | sh ``` Install prebuilt binaries via powershell script ```sh powershell -ExecutionPolicy Bypass -c "irm https://github.com/get-tmonier/argot/releases/download/v0.2.128/argot-installer.ps1 | iex" ``` Install prebuilt binaries into your npm project ```sh npm install @tmonier/[email protected] ``` Download argot 0.2.128 | File | Platform | Checksum | …View on GitHub ↗ -
Release notes excerpt
Install argot 0.2.127 Install prebuilt binaries via shell script ```sh curl --proto '=https' --tlsv1.2 -LsSf https://github.com/get-tmonier/argot/releases/download/v0.2.127/argot-installer.sh | sh ``` Install prebuilt binaries via powershell script ```sh powershell -ExecutionPolicy Bypass -c "irm https://github.com/get-tmonier/argot/releases/download/v0.2.127/argot-installer.ps1 | iex" ``` Install prebuilt binaries into your npm project ```sh npm install @tmonier/[email protected] ``` Download argot 0.2.127 | File | Platform | Checksum | …View on GitHub ↗
FAQ
Does Argot require a cloud account, API key, or paid model?
Does it upload source code or repository history?
ARGOT_OFFLINE=1 prevents network use.Does a clean check prove that the change is correct?
Will CI automatically retrain the repository model?
What can make the results unreliable?
Thanks — we use this to improve the page.