codestral-review

codestral-review is a skill for Claude Code from Swih/mistral-mcp. It costs 63 tokens per session (589 once invoked), scanned A, original, MIT.

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

In plain words
What is it for?
Use it to review a staged change or recent commit, with extra attention to the area most relevant to the files being changed.
Why use it?
It provides a focused review of a change before it is merged, including risks that may be easy to miss manually.

Skill for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Part of the mistral-mcp plugin — 11 skills shipped together

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

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/swih/mistral-mcp/codestral-review
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.

agentmods badge for codestral-review

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.

agentmods 80×15 button for codestral-review

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 63 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 589 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00063 $0.00589
Opus 5 $0.00032 $0.00295
Sonnet 5 $0.00013 $0.00118
Haiku 4.5 $0.00006 $0.00059

Measured 10d ago against content hash 745afd3fda7e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, 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 10d 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 · 57 lines

What it actually says

Codestral code review

You drive a focused code review of a diff using the Mistral codestral-latest model.

Workflow

Step 1 — Fetch the diff

If $ARGUMENTS contains a unified diff, use it. Otherwise:

  1. Check git diff --staged first (most likely intent)
  2. If empty, fall back to git diff HEAD~1..HEAD (last commit)
  3. If still empty, ask the user which range to review

Step 2 — Auto-detect the review focus

Inspect file paths and diff content to pick the most relevant lens:

Signal Focus
Files touching auth/, crypto/, secrets, .env, JWT/OAuth code, SQL queries with string concat, eval, file uploads security
Hot loops, big-O changes, async/parallelism, caching layer, DB queries, benchmark files performance
Public API surface: exported symbols, route handlers, schemas/contracts, breaking signature changes api_design
Anything else (refactor, bug fix, feature work) correctness

If multiple apply, ask the user which to prioritize, or run two passes with different focus values.

Step 3 — Run the review

Call the MCP prompt codestral_review from the mistral server with:

  • diff : the diff from step 1
  • focus : the lens from step 2

Pass the resulting messages to mistral_chat:

  • model : codestral-latest
  • temperature : 0.2 (deterministic critique)
  • max_tokens : 1500

Output format

The review must end with a verdict: ship, change-requested, or block.

Findings should be:

  • Concrete: cite exact lines or token ranges from the diff
  • High-signal: prefer 3 strong findings over 10 shallow ones
  • No invented issues: only flag real risks visible in the diff

Examples

  • /mistral-mcp:codestral-review — auto-detect from git diff --staged
  • /mistral-mcp:codestral-review security — force the security lens
  • /mistral-mcp:codestral-review <diff text> — review a pasted diff
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.

  1. 10d 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 today), licensed MIT. It adds 63 tokens to every session and 589 once invoked, about $0.0003 per session on Opus 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.