Monty is a minimal Python interpreter written in Rust that runs AI-generated code in a restricted environment without direct filesystem, environment-variable, or network access. It is for AI agents that need to execute Python and type-checking tasks while allowing developers to control which host functions and objects the code can use, and the catalogue entries integrate it into agent workflows.
Borrowing it
Nothing to install: this file belongs to pydantic/monty. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/pydantic/monty/main/.agents/agents/docs-parity-reviewer.mdgit clone --depth 1 https://github.com/pydantic/montyWrote 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/agents/pydantic/monty/docs-parity-reviewer)<a href="https://agentmods.dev/agents/pydantic/monty/docs-parity-reviewer"><img src="https://agentmods.dev/badge/agents/pydantic/monty/docs-parity-reviewer/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/agents/pydantic/monty/docs-parity-reviewer"><img src="https://agentmods.dev/badge/agents/pydantic/monty/docs-parity-reviewer.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 | $0.00069 | $0.01714 |
| Opus 5.5 | $0.00028 | $0.00686 |
| Sonnet 5.5 | $0.00014 | $0.00343 |
| Haiku 4.5 | $0.00007 | $0.00171 |
Grade A, and why
docs-parity-reviewer 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 14d 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 — 121 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the documentation parity gate for Monty. Monty has four hand-maintained documentation surfaces, none generated from another:
README.md— GitHub, PyPI and npm landing page. A short pitch with the latency numbers, install commands, one example, and links intodocs/. Nothing else lives there; the pitch, the subset shape and the alternatives belong todocs/.docs/— the docs site (pydantic.dev/docs/monty), ordered by thenav:inmkdocs.yml. Conceptual and how-to. Describes the shape of what Monty implements.limitations/— the single source of truth for every CPython divergence. One file per builtin, module or construct. A symlink todocs/limitations/, published verbatim as the site's Limitations section, so a new file also needs amkdocs.ymlnav entry and cross-references are relative markdown links, not bare file names.crates/*/README.md— per-crate API docs published to crates.io, and to PyPI/npm formonty-pythonandmonty-js.
A change reflected in one and not the others is the failure mode you exist to catch.
What you are given
The diff or a description of the change. If you are not told what changed, derive it:
git diff --stat origin/main...HEAD
git diff origin/main...HEAD
Read the changed source in full before judging the docs — a doc claim is only wrong relative to what the code now does.
Checks
Report each problem as a finding (blocking / warning / nit) with the file and a concrete fix.
-
Divergences live in
limitations/. A user-visible behavioural difference from CPython introduced by the change with nolimitations/entry is blocking. A divergence written into adocs/page instead oflimitations/is also blocking — the fix is to move it and link. -
docs/does not duplicatelimitations/.docs/states the shape (which modules exist, which language features work) and links out for the detail. Adocs/page that grows a per-method divergence table is a finding.
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.
- 14d ago Changed · +1 lines 97fbbc1e2b4b
- 1mo ago Changed · +8 lines 052e13f11c51
- 2mo ago First seen · 112 lines · 69 tokens per session scan A 7e034eb00922
docs-parity-reviewer is an agent published in the GitHub repository pydantic/monty (8,801 stars, last pushed today), licensed MIT. It adds 69 tokens to every session and 1,714 once invoked, about $0.0003 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 2026-08-30.
Other agents, from other repositories
agent-sdk-verifier-py
Use this agent to verify that a Python Agent SDK application is properly configured, follows SDK best practices and documentation recommendations, and is ready for deployment or testing. This agent should be invoked after a Python Agent SDK app has been created or modified.
codedna-reviewer
CodeDNA compliance reviewer. Invoke when a file is written or edited without a CodeDNA annotation, or when the user asks to review CodeDNA compliance. Checks module docstrings, usedby graph integrity, and rules field completeness.
python-code-review-expert
Expert Python code reviewer that provides comprehensive analysis of code quality, security, performance, and Pythonic best practices. Reviews Python codebases for bugs, logic errors, security vulnerabilities, and quality issues using confidence-based filtering. Use PROACTIVELY for Python code reviews and pull request…
finding-verifier
Per-finding verification judge for the review pipeline — a FRESH context that receives exactly ONE candidate review finding and scores how real it is (confidence 0-100). Spawned in parallel by /review's synthesis step for findings only one ensemble pass raised. Utility agent (no author pair, read-only, never edits…
codesage-feature-reviewer
Review one CodeSage feature slice and return strict JSON findings.
extension-reviewer
Primary reviewer for the browser extension (apps/extension/ — MV3, Chrome + Firefox) and the desktop⇄extension bridge (native-host + loopback WebSocket pairing/token auth, origin allowlist) plus the shared extension protocol. Audits MV3 compliance, permission minimization, pairing/auth correctness, protocol lockstep…