xliff-mcp-server AGENTS.md

xliff-mcp-server AGENTS.md is an instructions file for Codex, OpenCode from langlink-localization/xliff-mcp-server. It costs 320 tokens per session, scanned A, original, MIT.

Repository instructions for an XLIFF MCP server, a Python service that lets coding agents parse, check, export, and rewrite localization files. They describe the project structure, commands, and rules for handling translation data.

In plain words
What is it for?
Use them when maintaining or extending the XLIFF MCP server, especially when running checks, changing containers, or modifying translation workflows.
Why use it?
They give an agent the project context and safe working rules before it changes code. This reduces broken commands, changed output formats, lost translation tags, and accidental storage of confidential files.

Instructions file for CodexOpenCode

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.

agentmods
npx agentmods add instructions/langlink-localization/xliff-mcp-server/agents-md
Clone the repo
git clone --depth 1 https://github.com/langlink-localization/xliff-mcp-server

Made for: Codex, OpenCode.

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 xliff-mcp-server AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/langlink-localization/xliff-mcp-server/agents-md.svg)](https://agentmods.dev/instructions/langlink-localization/xliff-mcp-server/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/langlink-localization/xliff-mcp-server/agents-md"><img src="https://agentmods.dev/badge/instructions/langlink-localization/xliff-mcp-server/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 320 This file is loaded in full into every session.
When invoked 320 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.00320 $0.00320
Opus 5 $0.00160 $0.00160
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 5d ago against content hash 87d465c7e9c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

xliff-mcp-server AGENTS.md 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 5d 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.

AGENTS.md · 25 lines

What it actually says

XLIFF MCP Server

Repository purpose

  • Python MCP server for parsing, validating, exporting, and rewriting XLIFF/TMX content, with a separate agent-readable skills/ module.

Key entrypoints

  • xliff_mcp/ owns MCP tools, prompts, resources, and runtime workflows; skills/ owns standalone guidance.
  • pyproject.toml, Dockerfile, docker-compose.yml, and .env.example are the package and runtime contracts.

Canonical commands

  • Install development dependencies with pip install -e '.[dev]'.
  • Run ruff check ., python -m pytest -q, and python -m compileall -q xliff_mcp tests.
  • Run ruff format on Python files you change; do not whole-tree reformat unless asked.
  • Validate container changes with docker compose config.

Working rules

  • Preserve inline tags, segment identity, language metadata, replacement counts, and declared CSV/JSON output contracts.
  • Keep agent Skill guidance separate from MCP runtime registration; update both only when their shared behavior changes.
  • Treat user-supplied localization files as potentially confidential; do not persist inputs, translated content, exports, or raw tool payloads.
  • Do not add new MCP tools or change schemas without updating tests and README tool contracts.

Validation

  • Add focused parser and round-trip tests for XLIFF/TMX behavior changes, including malformed input and tag preservation.
  • Run MCP registration tests when tools, prompts, resources, or workflow mappings change.
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. 5d ago First seen · 25 lines · 320 tokens per session scan A 87d465c7e9c8

Subscribe to this mod's changes

xliff-mcp-server AGENTS.md is an instructions file published in the GitHub repository langlink-localization/xliff-mcp-server (2 stars, last pushed 11d ago), licensed MIT. It adds 320 tokens to every session, about $0.0016 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 2026-08-31.

Related

Other instructions, from other repositories