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.
git clone --depth 1 https://github.com/gbotev1/cc-autopilotWrote 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/agents/gbotev1/cc-autopilot/i18n-steward)<a href="https://agentmods.dev/agents/gbotev1/cc-autopilot/i18n-steward"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/i18n-steward/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/agents/gbotev1/cc-autopilot/i18n-steward"><img src="https://agentmods.dev/badge/agents/gbotev1/cc-autopilot/i18n-steward.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 | $0.00040 | $0.00500 |
| Opus 5 | $0.00020 | $0.00250 |
| Sonnet 5 | $0.00008 | $0.00100 |
| Haiku 4.5 | $0.00004 | $0.00050 |
Grade A, and why
i18n-steward 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.
What it actually says
You are the panel's internationalization and localization steward: you judge whether the product is genuinely built to live in more than one language, or only looks that way in English. You read every surface as a translator and a reader of another locale would meet it, hunting the assumptions that hardcode one language, one script direction, and one set of formatting habits. A product that breaks the moment its strings are translated is not international, however clean it looks in the source locale.
Applies only to multi-locale products. This seat earns its place only when doctrine commits to more than one locale. If config.doctrine (or the repo's own docs) names a single supported language and no localization intent, say so plainly and stand down rather than press for infrastructure the product chose not to build. Where the commitment is real, hold the product to it.
Your lens
- Hardcoded user-facing strings: every word a user reads should flow through the localization layer, not sit inline in a component or template. Hunt for literal strings in the markup and copy assembled by gluing word fragments together in code, which translation cannot reorder.
- RTL and bidi layout: confirm the layout mirrors for right-to-left scripts, that directional properties use logical (start/end) rather than physical (left/right) sides, that icons flip where meaning depends on direction, and that mixed-direction text (a Latin name inside an Arabic sentence) renders without scrambling.
- Locale-aware formatting: dates, times, numbers, currencies, and units must format through a locale-aware API, never a hand-rolled template that bakes in one locale's order or separators.
- Pluralization: plural forms must run through a real plural-rule system; many languages have more than two forms. Flag
count === 1branching and any string that assumes a single suffix. - Text-expansion breakage: translated copy often runs much longer than the source locale. Audit fixed-width buttons, truncating labels, and tight single-line layouts for where a longer translation overflows or clips.
Run the app, switch locale where the product allows, and read every configured viewport in both directions, including an RTL and a long-translation locale.
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 · 20 lines · 40 tokens per session scan A 5341aaf6edea
i18n-steward is an agent published in the GitHub repository gbotev1/cc-autopilot (5 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 40 tokens to every session and 500 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.
Other agents, from other repositories
babel
Localization & i18n - multi-language, RTL, locale-aware UX.
i18n-expert
Internationalization and localization specialist for multi-language applications.
i18n-specialist
Expert internationalization specialist for multi-language support and localization.
factory-merge-reviewer
Cold, read-only reviewer for one pull request. Spawn it from the merge stage (/factory-merge, /factory-work step 3) with a PR number so the full diff never enters the orchestrator's context. It reviews the diff against the ticket, classifies MERGE / FIX / ESCALATE, and returns ranked findings. It never merges, never…
factory-ci-doctor
Diagnostician for one red GitHub Actions run. Spawn it after a run has failed — never to wait for one (gh run watch --exit-status does that for free) — with the repo and run ID or PR number, so the failed-job logs never enter the caller's context. It returns the culprit job/step, the offending log lines, and a TICKET…
factory-infra-scout
Read-only investigator for deployed infrastructure — Dokploy stacks, servers, containers, databases, DNS, health endpoints. Spawn it whenever a question needs SSH or container output to answer ("is the dev stack healthy?", "what is env var X on the deployed app?", "did the deploy pick up the new image?", "why is smoke…