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/indranilbanerjee/contentforgeWrote 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/commands/indranilbanerjee/contentforge/translate)<a href="https://agentmods.dev/commands/indranilbanerjee/contentforge/translate"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/contentforge/translate/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/commands/indranilbanerjee/contentforge/translate"><img src="https://agentmods.dev/badge/commands/indranilbanerjee/contentforge/translate.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 | $0.00019 | $0.00478 |
| Opus 5.5 | $0.00008 | $0.00191 |
| Sonnet 5.5 | $0.00004 | $0.00096 |
| Haiku 4.5 | $0.00002 | $0.00048 |
Grade A, and why
translate 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 21d 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
Translate
This command is a thin wrapper. The complete translation procedure lives in
skills/cf-translate/SKILL.md — read that file and execute
it end to end. Do not improvise a different flow from this wrapper.
Trigger
User runs /contentforge:translate or asks to translate content, localize for a market, or
create multilingual versions.
Gather inputs
If not provided in the arguments, ask before proceeding:
- Content source — Google Drive URL, local file path, requirement ID (e.g.,
REQ-001), or pasted content - Target language — a language code from the supported list in
skills/cf-translate/SKILL.md(es, fr, de, pt, it, nl, ja, zh, ko, ar, hi, ru, pl, tr, vi). Multiple languages allowed:--language=es,fr,de - Localization level (optional, default
adapted) —literal|adapted|transcreated - Optional — regional variant (e.g.,
es-MXvses-ES), brand profile for multilingual voice mapping, target-market SEO keywords
Execute
Follow skills/cf-translate/SKILL.md in full:
source analysis → element classification (translatable vs immutable) → translation →
brand voice mapping via config/multilingual-patterns.json → citation preservation
(URLs/DOIs never change) → SEO localization → target-language humanization →
quality verification → output via the brand's tracking backend.
After translation
Ask: "Would you like me to:
- Translate into additional languages?
- Publish the translated version? (
/contentforge:publish) - Create social media posts in the translated language? (
/contentforge:social-adapt) - Review a specific section for cultural accuracy?
- Generate a side-by-side comparison of source and translation?"
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.
- 21d ago Changed · +1 lines · +3 tokens per session aebe282ca364
- 2mo ago First seen · 42 lines · 16 tokens per session scan A 3aae526c5294
translate is a command published in the GitHub repository indranilbanerjee/contentforge (32 stars, last pushed yesterday), licensed MIT. It adds 19 tokens to every session and 478 once invoked, about $0.0001 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 2026-08-30.
Other commands, from other repositories
engagement
Drive the 12-Part engagement by subcommand: start, next, status, validate, loop. "advance to the next part".
translate
Translate content into 15 languages, keeping brand voice and citations. "localize this article".
status
Show production status for the active brand and month. "where are we on this month".
new-month
Start a new month for a brand: folder and settings; a calendar to load -> parse-calendar; ideas -> ideate-month. "start a new month for this brand".
keywords
Run tiered keyword intelligence - ideas, competitor gaps, or CSV import.
monday-report
Write a stakeholder-shareable weekly summary of what moved, shipped, and needs a decision.