What is codestral-review?

A code-review tool that examines a code change and comments on its likely correctness, performance, security, or public-interface impact.

Use it to review a staged change or recent commit, with extra attention to the area most relevant to the files being changed.

It provides a focused review of a change before it is merged, including risks that may be easy to miss manually.

codestral-review — Skill for Claude Code by Swih/mistral-mcp

Install

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.

Any agent

npx skills add Swih/mistral-mcp --skill codestral-review

Clone the repo

git clone --depth 1 https://github.com/Swih/mistral-mcp

Made for: Claude Code.

Or install mistral-mcp, the plugin that ships this one along with the rest of its 11 skills.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/swih/mistral-mcp/codestral-review/github.svg)](https://agentmods.dev/skills/swih/mistral-mcp/codestral-review)

Your own site

<a href="https://agentmods.dev/skills/swih/mistral-mcp/codestral-review"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/codestral-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.

Your own site · 80×15

<a href="https://agentmods.dev/skills/swih/mistral-mcp/codestral-review"><img src="https://agentmods.dev/badge/skills/swih/mistral-mcp/codestral-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 40 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 414 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

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	$0.00040	$0.00414
Opus 5.5	$0.00016	$0.00166
Sonnet 5.5	$0.00008	$0.00083
Haiku 4.5	$0.00004	$0.00041

Measured 1mo ago against content hash f9c4b83849cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

codestral-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 1mo 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.

claude-plugin/skills/codestral-review/SKILL.md · 18 lines

What it actually says

Codestral code review

Use mistral_chat in core, metier-docs, admin, or a compatible self-hosted endpoint. Check mistral://capabilities for availability.

Use the supplied diff or requested Git range. Otherwise inspect git diff --staged, then git diff if nothing is staged. If both are empty, request a range rather than silently reviewing an unrelated commit.
Honor the requested focus, or select correctness, performance, security, or api_design from the actual change. Default to correctness when no narrower lens applies.
Retrieve the MCP prompt codestral_review with diff and focus. Prompts return messages; they do not run the review.
Convert each text message from {role, content: {type: "text", text: "..."}} to {role, content: "..."} and call mistral_chat with that messages array. Optional sampling fields are temperature and max_tokens.

Omit model to honor the configured chat default. For an explicit Codestral request, check mistral://models for an available identifier and confirm the endpoint supports chat with it. Report unavailable model selection instead of inventing an alias. codestral_fim requires prompt and suffix and is intended for code insertion.

Read structuredContent.text only after checking isError. Verify findings against the diff and relevant surrounding code. Report concrete defects with accurate file and line references, impact, and any uncertainty. End with ship, change-requested, or block, scoped to the code actually reviewed. Do not imply that tests ran unless they did.

Changes

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.

1mo ago Changed · -39 lines · -23 tokens per session f9c4b83849cd
2mo ago First seen · 57 lines · 63 tokens per session scan A 745afd3fda7e

Subscribe to this mod's changes

codestral-review is a skill published in the GitHub repository Swih/mistral-mcp (15 stars, last pushed 1mo ago), licensed MIT. It adds 40 tokens to every session and 414 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 2026-08-30.

Claude Code Code review Security TypeScript cursor mcp mistral-ai model-context-protocol

code-review

Reviews code changes, pull requests, and diffs for correctness, security, performance, and style. Use when the user submits a PR for review, asks to review a diff or code snippet, or requests a quality check on recent changes.

0xranx/golembot · 51 tokens

pr-reviewer

Review a requested pull request, branch diff or completed task against its actual scope, source and checks. Prepare evidence and comments; post or record a human verdict only when explicitly authorized.

getpapi/papi · 40 tokens

gitlab-review

Review a GitLab merge request, inspect changes and discussions, or prepare and post explicitly requested review feedback. Use for GitLab MRs and review follow-ups, not GitHub pull requests or automatic approval/merge.

structured-world/gitlab-mcp · 47 tokens

spec-harness-generate-agents

Bind the 6 SDD agents to THIS project's rules — fill each agent's GEN:rules region with its concern's real rules (implementer←Coding, tester←Testing+commands, reviewer←Reviewing, researcher/planner←Architecture, verifier←goal). Use when Malik says 'generate the agents', 'make the agents project-specific', 'bind agents…

chohra-med/expo_boilerplate · 0 tokens

spec-harness-build

Run the SDD pipeline over tasks.md: implement → test → VERIFY → review, one task at a time, under the ratchet. Use when Malik says 'build it', 'run the pipeline', 'implement the tasks', or 'ship this feature'. Each task gated by the separate verifier; lessons harvested by learn.