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.
npx skills add CALLE-AI/awesome-phone-call-agents --skill call-cross-lingual-emotion-preservationgit clone --depth 1 https://github.com/CALLE-AI/awesome-phone-call-agentsWrote 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/calle-ai/awesome-phone-call-agents/call-cross-lingual-emotion-preservation)<a href="https://agentmods.dev/skills/calle-ai/awesome-phone-call-agents/call-cross-lingual-emotion-preservation"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-cross-lingual-emotion-preservation/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/calle-ai/awesome-phone-call-agents/call-cross-lingual-emotion-preservation"><img src="https://agentmods.dev/badge/skills/calle-ai/awesome-phone-call-agents/call-cross-lingual-emotion-preservation.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00070 | $0.01030 |
| Opus 5.5 | $0.00028 | $0.00412 |
| Sonnet 5.5 | $0.00014 | $0.00206 |
| Haiku 4.5 | $0.00007 | $0.00103 |
Grade A, and why
call-cross-lingual-emotion-preservation 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 29d 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 — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.
call-cross-lingual-emotion-preservation
When the message crosses a language, does the urgency survive?
language-bridge-call relays a request across languages in two legs. This
skill is an experimental QA companion: it compares English urgency-marker
levels in supplied text from both legs. It does not measure actual emotion
or prove that a translation preserved it. A phrase such as "today, immediately, please"
that arrives as "sometime this week would be fine" is a failed relay even
when the words are translated correctly.
When To Use
- after a
language-bridge-callrelay, to check the requester's urgency survived the second leg - after any translated CALL-E call where emotional subtext matters (escalations, care requests, time-critical arrangements)
- to generate an intensity-calibrated relay goal for the next
plan_call
When Not To Use
- to relay or translate anything; use
language-bridge-call - to detect sarcasm or stated-vs-meant mismatch; use
call-verbal-irony-detector - to audit the relay callee's own emotions; only the relay agent's expressed intensity is measured, because the relay speaks on the requester's behalf
- on non-English source OR relay text; the same English-only lexicon scores both. Provide operator-prepared English translations when needed; this script does not translate. A target-language parameter does not change the scorer. Non-English text can produce misleading low scores.
Workflow
Analyze a relay
python3 scripts/emotion_preservation.py analyze --source-context path/to/source.json --relay-transcript path/to/relay.json
--source-context accepts the requester's call-result JSON (callee turns
are used) or a plain-text operator note. --relay-transcript accepts the
relay leg's CALL-E result (nested get_call_run or flat fixture shape).
Both texts must be English or separately translated into English by the
operator. The script does not detect or enforce language eligibility.
Emits a card:
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 29d ago First seen · 96 lines · 70 tokens per session scan A aac5d3991a4a
call-cross-lingual-emotion-preservation is a skill published in the GitHub repository CALLE-AI/awesome-phone-call-agents (109 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 1,030 once invoked, about $0.0003 per session on Opus 5.5. 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 2026-09-21.
Other skills, from other repositories
chinese-documentation
A Chinese technical-documentation style guide covering spacing, punctuation, numbers, terminology, and links when Chinese and English appear together.
azure-ai-translation-text-py
Azure AI Text Translation SDK for real-time text translation, transliteration, language detection, and dictionary lookup. Use for translating text content in applications. Triggers: "text translation", "translator", "translate text", "transliterate", "TextTranslationClient".
harden
Improve interface resilience through better error handling, i18n support, text overflow handling, and edge case management. Makes interfaces robust and production-ready. Use when the user asks to harden, make production-ready, handle edge cases, add error states, or fix overflow and i18n issues.
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.
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.
docs-governance
Use when writing, restructuring, auditing, or reviewing Cherry Studio repository documentation, READMEs, JSDoc, comments, Agent instructions, or paired English/Chinese docs, including source-linked documentation impact checks.