backfill

A localization workflow that fills missing or untranslated text in every language file using a master language as the source. Localization means adapting an application for different languages.

In plain words
What is it for?
It helps scan locale files, identify missing or untranslated keys, translate them from the master locale, and use the project's internationalization settings.
Why use it?
It removes the need to find and translate incomplete entries manually across multiple locale files.

Skill for Claude CodeCodex

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 skills/ericfitz/skills/backfill
Any agent
npx skills add ericfitz/skills --skill backfill
Clone the repo
git clone --depth 1 https://github.com/ericfitz/skills

Made for: Claude Code, Codex.

Per session 36 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,742 The whole file, excluding the scripts and references it only reads on demand.
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 $0.00036 $0.01742
Opus 5 $0.00018 $0.00871
Sonnet 5 $0.00007 $0.00348
Haiku 4.5 $0.00004 $0.00174

Measured 2d ago against content hash f2c3e9e93ea7, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

backfill 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 2d 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.

loc/skills/backfill/SKILL.md · 222 lines

How it starts

The opening of the file, as written. The whole thing — 222 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Localization Backfill

Translate every missing or untranslated key across all i18n locale files using the master locale as the source.

This command orchestrates a set of skills; the skills do not assume any particular i18n tooling. Project-specific paths and commands come from .claude/i18n.config.json.

Bundled scripts

  • scripts/find_duplicate_localizations.py — bundled dedupe analyzer used in Step 1 of this skill.
  • The translation analysis itself runs through [[analyze]], which bundles its own scripts/check-i18n.py.

When you see ${CLAUDE_PLUGIN_ROOT} below, it refers to this plugin's install root — typically ~/.claude/plugins/cache/efitz-skills/loc/<version>/. If Claude Code does not pre-substitute the variable when you read this file, resolve it yourself: locate the directory containing this SKILL.md, walk up to the plugin root, and use that absolute path. Do NOT fall back to the legacy path ~/Projects/skills/commands/localization-backfill.scripts/.

Configuration

Same config used by the i18n skill family — see [[analyze]] for the full schema. Required fields:

  • locales_dir
  • master_locale
  • file_extension

Optional:

{
  "format_command":    "<shell command that normalizes formatting, e.g. 'pnpm run format'>",
  "dedupe_plan_file":  "<path where the dedupe script writes its plan, default 'localization_dedup_plan.txt'>"
}

If format_command is absent, the format step is skipped.

Process

Step 1: Deduplicate

Run the bundled dedupe script (${CLAUDE_PLUGIN_ROOT} is the root directory of this plugin):

uv run "${CLAUDE_PLUGIN_ROOT}/scripts/find_duplicate_localizations.py" \
  --skippolicy --reference

The script reads .claude/i18n.config.json to find the master locale, then writes its plan to localization_dedup_plan.txt in the current directory (override with -o).

Then:

  1. Read the plan file.
  2. If it contains REFER recommendations:
    1. Back up locale files: mkdir -p /tmp/i18n-dedup-backups && cp <locales_dir>/*.<ext> /tmp/i18n-dedup-backups/.
    2. Apply each REFER change to the master locale — replace the literal value with a {{reference}} template.
    3. Apply the same reference change to every non-master locale (jq filter).
    4. Run format_command from config if present.
    5. Re-run the dedupe script to verify zero duplicates remain.
  3. If no duplicates, continue to step 2.

Read the full file on GitHub · 222 lines

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. 2d ago First seen · 222 lines · 36 tokens per session scan A f2c3e9e93ea7

Subscribe to this mod's changes

backfill is a skill published in the GitHub repository ericfitz/skills (2 stars, last pushed 9d ago), licensed Apache-2.0. It adds 36 tokens to every session and 1,742 once invoked, about $0.0002 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 skills, from other repositories

dsh-translate-docs

Manually run the extended DeepSeek Harness bilingual-document workflow, including generated briefings, delegated prose translation, whole-document translation, and scoped pairing verification.

deepseek-ai/deepseek-harness · 37 tokens

i18n-localization

Internationalization and localization patterns. Detecting hardcoded strings, managing translations, locale files, RTL support.

vudovn/ag-kit · 27 tokens

translate-skill

将 mattpocock/skills 的内容翻译、刷新或复核到简体中文本地化仓库 vinvcn/mattpocock-skills-zh-CN 时使用这个项目级 skill。适用于 skill files、README content、CLAUDE.md、CONTEXT.md、docs,以及其他需要保留行为关键 identifiers 的上游用户可见内容。.

vinvcn/mattpocock-skills-zh-CN · 84 tokens

seedance-vocab-ja

This skill should be used when the user asks for Japanese Seedance 2.0 prompt wording, Japanese cinematic vocabulary, or translation of camera, lighting, action, VFX, audio, and production terms into Japanese.

Emily2040/seedance-2.0 · 50 tokens

asc-subscription-localization

Bulk-localize subscription, subscription-group, and in-app purchase display names across App Store locales using asc, including API 4.4.1 version-scoped v2 resources. Use when filling or updating subscription/IAP names and descriptions without App Store Connect UI work.

rorkai/app-store-connect-cli-skills · 60 tokens

harden

Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready.

childrentime/reactuse · 32 tokens