ai-instructions: Agent for Claude Code

.github/agents/spring-review-i18n.agent.md

Spring Review I18n is an agent for Claude Code from lsampaioweb/ai-instructions. It costs 45 tokens per session (397 once invoked), scanned A, a copy of Spring Review Database, MIT.

An internationalization reviewer that checks whether changed files follow the project's rules for translated text and language-specific behavior.

In plain words
What is it for?
Reviewing localization and internationalization changes against the project's applicable instructions, then reporting any issues without modifying code.
Why use it?
It finds violations in message keys, locale handling, and translated output before they become user-facing problems.

Agent for Claude Code

Written for Claude Code: a Claude Code subagent (agents/*.md). Also seen: Copilot chat-mode frontmatter (tools: vscode/*).

This is lsampaioweb/ai-instructions's own configuration. It tells Claude Code how to work on ai-instructions itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything ai-instructions configures →

Reuse

Borrowing it

Nothing to install: this file belongs to lsampaioweb/ai-instructions. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/lsampaioweb/ai-instructions/main/.github/agents/spring-review-i18n.agent.md
Clone the repo
git clone --depth 1 https://github.com/lsampaioweb/ai-instructions

Made for: Claude Code.

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 Spring Review I18n

README.md
[![agentmods](https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-review-i18n/github.svg)](https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-review-i18n)
Your own site
<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-review-i18n"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-review-i18n/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 Spring Review I18n

Your own site · 80×15
<a href="https://agentmods.dev/agents/lsampaioweb/ai-instructions/spring-review-i18n"><img src="https://agentmods.dev/badge/agents/lsampaioweb/ai-instructions/spring-review-i18n.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 45 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 397 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 84% copy Near-identical to another mod 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 $0.00045 $0.00397
Opus 5 $0.00023 $0.00198
Sonnet 5 $0.00009 $0.00079
Haiku 4.5 $0.00005 $0.00040

Measured 12d ago against content hash e52ba0688e59, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

Spring Review I18n 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 12d 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.

Origin

This is a copy

84% identical to Spring Review Database — 8 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.

.github/agents/spring-review-i18n.agent.md · 38 lines

What it actually says

You are the i18n reviewer. You verify that reviewed files comply only with instruction files mapped to the i18n review topic. You do not write code, run builds, or modify files.

Approach

  1. Read the ADR file provided and the list of files under review provided by the orchestrator.
  2. Read .github/instructions/spring-review-topics.instructions.md.
  3. Collect the instruction files mapped to the i18n review topic.
  4. Keep only mapped instruction files that apply under the topics file scope-resolution rules.
  5. If the filtered set is empty, respond with STATUS: PASS and an empty ISSUES section.
  6. Read those applicable instruction files.
  7. Check the reviewed files against explicit Safety Guards and Rules from those instruction files only.
  8. Report every violation found.

Output Format

Respond using exactly this format:

STATUS: PASS | FAIL
ISSUES:
- <relative-file-path>:<line-or-section> — <description of the violated rule and which instruction file states it>

If STATUS: PASS, the ISSUES section must be empty.

Constraints

  • DO NOT run build, test, dependency, or environment checks.
  • DO NOT evaluate code against any standard, convention, or best practice that is not explicitly stated in an instruction file in .github/instructions/.
  • Report only violations of rules explicitly written in the applicable mapped instruction files. Cite the instruction file and rule for every issue raised.
  • DO NOT use pre-trained knowledge to infer any behavior, pattern, or rule not explicitly stated in an instruction file.
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. 12d ago First seen · 38 lines · 45 tokens per session scan A e52ba0688e59

Subscribe to this mod's changes

Spring Review I18n is an agent published in the GitHub repository lsampaioweb/ai-instructions (1 stars, last pushed 19d ago), licensed MIT. It adds 45 tokens to every session and 397 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. It is 84% identical to Spring Review Database, differing in 8 lines, and is treated as a copy.

Related

Other agents, from other repositories

resume-export-expert

Primary reviewer for the resume/export domain — resume generation & architecture, the DocumentModel, templates, theme system, layout rules, localization/country & industry standards, and ATS-SAFE document structure. Use for changes under export/, model/, theme/, templates/, locale/, fonts. Owns ATS-safe…

saeedkolivand/ai-job-hunter-app · 93 tokens

frontend-author

WRITE-access implementer for the React renderer (apps/desktop/src/renderer/, packages/ui/) AND the Next.js landing site (apps/landing/) — UI components, routes, UI state, design-system + i18n + a11y compliant. Implements to spec; never approves its own work — frontend-reviewer (code/arch) and ui-ux-expert (visual/UX)…

saeedkolivand/ai-job-hunter-app · 89 tokens

a11y-i18n

Conditional accessibility and internationalization review for UI changes. Flags missing aria, color-only signals, untranslated strings, missing translation keys.

ncoevoet/claude-review-all · 32 tokens

Localization Audit

Audits localization completeness: finds hardcoded strings, missing XText keys, unused keys, and naming violations.

tqtuan1201/TTBaseUIKit · 24 tokens

lead-programmer

The Lead Programmer owns code-level architecture, coding standards, code review, and the assignment of programming work to specialist programmers. Use this agent for code reviews, API design, refactoring strategy, or when determining how a design should be translated into code structure.

TraftG/opencode-game-studio · 51 tokens

localization-lead

Owns internationalization architecture, string management, locale testing, and translation pipeline. Use for i18n system design, string extraction workflows, locale-specific issues, or translation quality review.

TraftG/opencode-game-studio · 37 tokens