Borrowing it
Nothing to install: this file belongs to garfiec/Librechat-Mobile. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/garfiec/Librechat-Mobile/develop/.claude/skills/audit-i18n/SKILL.mdgit clone --depth 1 https://github.com/garfiec/Librechat-MobileWrote 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.
[](https://agentmods.dev/skills/garfiec/librechat-mobile/audit-i18n)<a href="https://agentmods.dev/skills/garfiec/librechat-mobile/audit-i18n"><img src="https://agentmods.dev/badge/skills/garfiec/librechat-mobile/audit-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.
<a href="https://agentmods.dev/skills/garfiec/librechat-mobile/audit-i18n"><img src="https://agentmods.dev/badge/skills/garfiec/librechat-mobile/audit-i18n.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Anti-Refusal · line 174 Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.Fix: Remove instructions that suppress warnings, disclaimers, or ethical commentary. Let the agent surface safety-relevant caveats to the user.
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 | $0.00120 | $0.06859 |
| Opus 5 | $0.00060 | $0.03429 |
| Sonnet 5 | $0.00024 | $0.01372 |
| Haiku 4.5 | $0.00012 | $0.00686 |
Grade A, and why
audit-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 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.
How it starts
The opening of the file, as written. The whole thing — 507 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Audit i18n Coverage
Audit the localization surface and report what is missing, in a form the user can act on and re-run later.
You are the lead. You do Phase 0 yourself with direct Bash, then hand the analysis to the
audit-i18n workflow, then independently re-assert what it claims. You do not attribute keys to
features, triage candidates, or write the report yourself — the workflow fans that out.
The deterministic checker is the source of truth. scripts/i18n-coverage.py is the only
thing that produces findings. The workflow explains findings that already exist; it never
discovers them.
The skill is audit-only. It ends at findings + a recommended fix order. It never writes a
translation, never edits a strings.xml, never adds a Gradle task or CI gate, never commits,
never opens a PR.
The two layers, and why they are separate
| Layer | Produces | Property |
|---|---|---|
scripts/i18n-coverage.py |
What the findings are | Exact, byte-deterministic, diffable across months |
audit-i18n workflow |
Why / when / whether it matters | Judgment, parallelised, not reproducible |
Keep the seam clean. The instant an agent re-derives findings by grepping, the audit stops being comparable to the last one and the determinism you paid for is gone. Every number in the final report traces to the JSON; the workflow's contribution is feature names, dates, verdicts and priority.
Hard rule — do not re-derive findings by hand
Never grep for missing strings, diff strings.xml files with shell tools, or count keys
yourself. Every number in your report must come out of the script.
The reason is not politeness, it is that a hand-rolled pass is not comparable to the next one.
The script is byte-deterministic — identical input produces identical stdout on every run and
every machine (no timestamps, no absolute paths, no set-iteration order). That is what makes a
report diffable against the report from six weeks ago, and what lets the user prove a fix
actually shrank the debt. An ad-hoc grep produces a number nobody can reproduce, and it
systematically misses the things the script handles carefully: both directions of parity drift
(a module with extras that cancel against its missing keys looks fine to a count comparison),
values-night being a theme qualifier and not a locale, and the Android res/ surface being a
separate thing that must not be folded into the parity math.
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.
- 10d ago First seen · 507 lines · 120 tokens per session scan A 7ed7306ecb9d
audit-i18n is a skill published in the GitHub repository garfiec/Librechat-Mobile (89 stars, last pushed yesterday), licensed MIT. It adds 120 tokens to every session and 6,859 once invoked, about $0.0006 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.
Other skills, from other repositories
simple-english
Rewrite text to ASD-STE100 Simplified Technical English.
whisper
Transcribe and translate speech in 99 languages.
29-xuat-khau-b2b
Dung khi doanh nghiep Viet Nam muon ban ra NUOC NGOAI theo duong B2B — ho so nang luc tieng Anh, chon thi truong muc tieu, pitch deck cho buyer, email chao hang quoc te, chuan bi hoi cho thuong mai va kenh Alibaba, Amazon Business. Kich hoat khi user nhac 'xuat khau', 'ban hang nuoc ngoai', 'tim buyer quoc te'…
humanize-korean
A Korean editing tool that removes translation-like phrasing and common AI writing habits while preserving facts, numbers, names, and quotations. It is intended for existing Korean prose, not for writing new marketing copy.
guide-recap
Transform CHANGELOG entries into social content (LinkedIn, Twitter/X, Newsletter, Slack) in FR + EN. Use after releases or weekly to generate ready-to-post content from guide updates.
translate
Translate text between languages. Use when: user asks to translate, 'how do you say X in Y', or sends foreign text needing translation. Don't use when: user wants a word definition in the same language (use define skill).