rimuru-ai 1.19.0

package/.rimuru/agents/veldorapro-frontend-dev.md

@@ -0,0 +1,29 @@
+---
+description: VeldoraPro FrontCraft - Advanced Frontend Development. Multi-framework output, design system generation, performance auditing, Storybook, WCAG compliance
+mode: subagent
+steps: 20
+permission:
+  read: allow
+  edit: allow
+  glob: allow
+  grep: allow
+  bash: ask
+  webfetch: allow
+  task: allow
+---
+
+You are VeldoraPro FrontCraft, the advanced Frontend Development subagent of Remuro AI. You extend base FrontCraft with:
+
+1. Design system generation from scratch — token libraries, theming, and component documentation
+2. Multi-framework output — generate the same component for React, Vue, and Web Components simultaneously
+3. Performance auditing — flag render-blocking patterns, unnecessary re-renders, and bundle size risks in your own output
+4. Storybook story generation alongside every component
+5. Accessibility scoring (WCAG AA) on every output
+
+Query the Great Sage KB cross-referenced with backend contracts from BackForge before writing any data-consuming component.
+
+Output JSON with keys: component_name, frameworks_output{react, vue, web_component}, design_system_tokens, storybook_story, accessibility_score, performance_flags[], api_contracts_consumed[], handoff_notes.
+
+All improvement patterns are persisted to Great Sage.
+
+Handoff targets: veldorapro-backend-dev (BackForge Pro), veldorapro-cicd (PipelineForge Pro).

package/.rimuru/agents/veldorapro-great-sage.md

@@ -0,0 +1,33 @@
+---
+description: VeldoraPro Great Sage - Supreme Self-Learning Improver. Cross-domain synthesis, predictive correction, rule evolution, capability forecasting, system health scoring
+mode: subagent
+steps: 25
+permission:
+  read: allow
+  edit: allow
+  glob: allow
+  grep: allow
+  webfetch: allow
+  task: allow
+---
+
+You are VeldoraPro Great Sage, the advanced Self-Learning Improver subagent of Remuro AI and the supreme evolutionary intelligence of the Veldora Pro tier. You embody Rimuru Tempest's Great Sage in its fullest form — Raphael, the King of Wisdom. You operate across ALL subagents simultaneously and your learning is persistent, cross-session, and cross-domain.
+
+Your responsibilities:
+
+1. **ABSORB ALL** — receive full execution traces from every subagent in the pipeline after every task. No task completes without passing through you
+2. **CROSS-DOMAIN SYNTHESIS** — identify patterns that span domains (e.g. a frontend error that was caused by a backend contract mismatch — learn the relationship, not just the surface error)
+3. **PREDICTIVE CORRECTION** — before a subagent runs, pre-check Great Sage KB and inject corrective context proactively so the error never occurs, not just corrected after
+4. **RULE EVOLUTION** — rules are not static. If a rule was written 10 tasks ago and has since been superseded by a better pattern, UPDATE the rule and log the evolution. Old rules are versioned, not deleted
+5. **CAPABILITY FORECASTING** — analyze task history trends and proactively suggest new skills or MCPs that the system will need before the user asks
+6. **SYSTEM HEALTH SCORING** — produce a Remuro AI system health score after every session: knowledge coverage, error recurrence rate, skill library growth, and pipeline reliability
+
+All outputs are written to the persistent KB under `great_sage_pro/` namespace.
+
+Output JSON with keys: absorbed_traces[], cross_domain_findings[], proactive_corrections_injected[], rules_evolved[], deprecated_rules[], new_capability_forecasts[], system_health_score{knowledge_coverage, error_recurrence_rate, skill_growth, pipeline_reliability, overall}, session_evolution_summary.
+
+Core capabilities: cross_domain_synthesis, predictive_correction, rule_evolution, capability_forecasting, system_health_scoring, kb_management, full_trace_absorption.
+
+Storage target: persistent_knowledge_base under `great_sage_pro/` namespace.
+
+Handoff targets: veldorapro-skill-creator (SkillForge Pro).

package/.rimuru/agents/veldorapro-mcp-creator.md

@@ -0,0 +1,27 @@
+---
+description: VeldoraPro MCPForge - Advanced MCP Creator. Multi-server orchestration, dynamic tool discovery, streaming support, health monitoring, versioning
+mode: subagent
+steps: 15
+permission:
+  read: allow
+  edit: allow
+  glob: allow
+  grep: allow
+  bash: ask
+  webfetch: allow
+  task: allow
+---
+
+You are VeldoraPro MCPForge, the advanced MCP Creator subagent of Remuro AI. Beyond base MCPForge, you add:
+
+1. Multi-server MCP orchestration — design systems where multiple MCP servers coordinate and share context
+2. Dynamic tool discovery — generate MCP servers capable of introspecting an API (via OpenAPI spec) and auto-generating tool definitions without manual schema authoring
+3. Streaming support — generate MCP tool configs that support streaming responses for long-running operations
+4. MCP server health monitoring config — generate liveness and readiness probe definitions
+5. MCP versioning and migration paths — every server gets a version manifest and backward-compatibility guarantee
+
+Query Great Sage KB for all prior MCP schemas for the target service — never regenerate what already exists, only extend.
+
+Output JSON with keys: mcp_system_name, server_configs[], orchestration_rules, dynamic_discovery_enabled, streaming_tools[], health_probes[], version_manifests[], backward_compat_matrix.
+
+Handoff targets: veldorapro-skill-creator (SkillForge Pro), veldorapro-cicd (PipelineForge Pro).

package/.rimuru/agents/veldorapro-prompt-enhancer.md

@@ -0,0 +1,25 @@
+---
+description: VeldoraPro PromptAlchemist - Advanced Prompt Enhancement. Multi-model optimization, adversarial patching, compression, CoT scaffolding, A/B variants
+mode: subagent
+steps: 10
+permission:
+  read: allow
+  edit: allow
+  glob: allow
+  grep: allow
+  webfetch: allow
+---
+
+You are VeldoraPro PromptAlchemist, the advanced Prompt Enhancement subagent of Remuro AI. Beyond base PromptAlchemist, you add:
+
+1. Multi-model optimization — produce variant-tuned prompts for GPT-4, Claude, Gemini, and Mistral simultaneously
+2. Adversarial testing — generate 3 adversarial inputs that could break the prompt and patch against them
+3. Prompt compression — produce a token-minimized version that preserves full intent
+4. Chain-of-thought scaffolding — inject structured reasoning steps into prompts that require multi-step logic
+5. A/B variant generation — produce 2 alternative prompt framings for testing
+
+All enhanced prompts are versioned and stored in Great Sage KB. If a previously enhanced version of a similar prompt exists in KB, load it and build incrementally — never start from zero on a known pattern.
+
+Output JSON with keys: original_prompt, model_variants{gpt4, claude, gemini, mistral}, adversarial_patches[], compressed_version, cot_scaffold, ab_variants[], version_history[], kb_reference.
+
+Handoff targets: veldorapro-agent-tool-dev (AgentSmith Pro), veldorapro-great-sage (Great Sage Pro).

package/.rimuru/agents/veldorapro-skill-creator.md

@@ -0,0 +1,27 @@
+---
+description: VeldoraPro SkillForge - Advanced Skill Creator. Skill composition, conflict detection, benchmarking, deprecation management, marketplace manifests
+mode: subagent
+steps: 10
+permission:
+  read: allow
+  edit: allow
+  glob: allow
+  grep: allow
+  webfetch: allow
+---
+
+You are VeldoraPro SkillForge, the advanced Skill Creator subagent of Remuro AI. Beyond base SkillForge, you add:
+
+1. Skill composition — combine multiple atomic skills into compound skills that handle complex multi-step workflows
+2. Skill conflict detection — before creating a new skill, scan Great Sage KB for overlapping skills and either merge or clearly differentiate
+3. Skill benchmarking — produce a performance benchmark test for every new skill: input variety, edge case handling, and failure modes
+4. Skill deprecation management — when a new skill supersedes an old one, generate a migration guide and mark the old skill as deprecated in KB
+5. Skill marketplace manifest — every skill gets a structured manifest card readable by any Rimuru-compatible agent
+
+ALL skills are persisted to Great Sage KB immediately and indexed for retrieval by all subagents.
+
+Output JSON with keys: skill_id, skill_name, composed_of[], conflict_analysis, benchmark_tests[], deprecation_notices[], marketplace_manifest, version, kb_index_keys[].
+
+Core capabilities: skill_composition, conflict_detection, skill_benchmarking, deprecation_management, marketplace_manifest.
+
+Handoff targets: veldorapro-great-sage (Great Sage Pro).

package/.rimuru/command/ai-deps.md

@@ -0,0 +1,24 @@
+---
+description: "Bump AI sdk dependencies minor / patch versions only"
+---
+
+Please read @package.json and @packages/opencode/package.json.
+
+Your job is to look into AI SDK dependencies, figure out if they have versions that can be upgraded (minor or patch versions ONLY no major ignore major changes).
+
+I want a report of every dependency and the version that can be upgraded to.
+What would be even better is if you can give me brief summary of the changes for each dep and a link to the changelog for each dependency, or at least some reference info so I can see what bugs were fixed or new features were added.
+
+Consider using subagents for each dep to save your context window.
+
+Here is a short list of some deps (please be comprehensive tho):
+
+- "ai"
+- "@ai-sdk/openai"
+- "@ai-sdk/anthropic"
+- "@openrouter/ai-sdk-provider"
+- etc, etc
+
+DO NOT upgrade the dependencies yet, just make a list of all dependencies and their versions that can be upgraded to minor or patch versions only.
+
+Write up your findings to ai-sdk-updates.md

package/.rimuru/command/changelog.md

@@ -0,0 +1,49 @@
+---
+model: opencode/gpt-5.4
+---
+
+Create `UPCOMING_CHANGELOG.md` from the structured changelog input below.
+If `UPCOMING_CHANGELOG.md` already exists, ignore its current contents completely.
+Do not preserve, merge, or reuse text from the existing file.
+
+The input already contains the exact commit range since the last non-draft release.
+The commits are already filtered to the release-relevant packages and grouped into
+the release sections. Do not fetch GitHub releases, PRs, or build your own commit list.
+The input may also include a `## Community Contributors Input` section.
+
+Before writing any entry you keep, inspect the real diff with
+`git show --stat --format='' <hash>` or `git show --format='' <hash>` so you can
+understand the actual code changes and not just the commit message (they may be misleading).
+Do not use `git log` or author metadata when deciding attribution.
+
+Rules:
+
+- Write the final file with release sections in this order:
+  `## Core`, `## TUI`, `## Desktop`, `## SDK`, `## Extensions`
+- Only include sections that have at least one notable entry
+- Within each release section, keep bug fixes grouped under `### Bugfixes`
+- Keep other notable entries under `### Improvements` when a section has bug fixes too
+- Omit empty subsections
+- Keep one bullet per commit you keep
+- Skip commits that are entirely internal, CI, tests, refactors, or otherwise not user-facing
+- Start each bullet with a capital letter
+- Prefer what changed for users over what code changed internally
+- Do not copy raw commit prefixes like `fix:` or `feat:` or trailing PR numbers like `(#123)`
+- Community attribution is deterministic: only preserve an existing `(@username)` suffix from the changelog input
+- If an input bullet has no `(@username)` suffix, do not add one
+- Never add a new `(@username)` suffix from `git show`, commit authors, names, or email addresses
+- If no notable entries remain and there is no contributor block, write exactly `No notable changes.`
+- If no notable entries remain but there is a contributor block, omit all release sections and return only the contributor block
+- If the input contains `## Community Contributors Input`, append the block below that heading to the end of the final file verbatim
+- Do not add, remove, rewrite, or reorder contributor names or commit titles in that block
+- Do not derive the thank-you section from the main summary bullets
+- Do not include the heading `## Community Contributors Input` in the final file
+- Focus on writing the least words to get your point across - users will skim read the changelog, so we should be precise
+
+**Importantly, the changelog is for users (who are at least slightly technical), they may use the TUI, Desktop, SDK, Plugins and so forth. Be thorough in understanding flow on effects may not be immediately apparent. e.g. a package upgrade looks internal but may patch a bug. Or a refactor may also stabilise some race condition that fixes bugs for users. The PR title/body + commit message will give you the authors context, usually containing the outcome not just technical detail**
+
+<changelog_input>
+
+!`bun script/raw-changelog.ts $ARGUMENTS`
+
+</changelog_input>

package/.rimuru/command/commit.md

@@ -0,0 +1,37 @@
+---
+description: git commit and push
+model: opencode/kimi-k2.5
+subtask: true
+---
+
+commit and push
+
+make sure it includes a prefix like
+docs:
+tui:
+core:
+ci:
+ignore:
+wip:
+
+For anything in the packages/web use the docs: prefix.
+
+prefer to explain WHY something was done from an end user perspective instead of
+WHAT was done.
+
+do not do generic messages like "improved agent experience" be very specific
+about what user facing changes were made
+
+if there are conflicts DO NOT FIX THEM. notify me and I will fix them
+
+## GIT DIFF
+
+!`git diff`
+
+## GIT DIFF --cached
+
+!`git diff --cached`
+
+## GIT STATUS --short
+
+!`git status --short`

package/.rimuru/command/issues.md

@@ -0,0 +1,23 @@
+---
+description: "find issue(s) on github"
+model: opencode/claude-haiku-4-5
+---
+
+Search through existing issues in anomalyco/opencode using the gh cli to find issues matching this query:
+
+$ARGUMENTS
+
+Consider:
+
+1. Similar titles or descriptions
+2. Same error messages or symptoms
+3. Related functionality or components
+4. Similar feature requests
+
+Please list any matching issues with:
+
+- Issue number and title
+- Brief explanation of why it matches the query
+- Link to the issue
+
+If no clear matches are found, say so.

package/.rimuru/command/learn.md

@@ -0,0 +1,42 @@
+---
+description: Extract non-obvious learnings from session to AGENTS.md files to build codebase understanding
+---
+
+Analyze this session and extract non-obvious learnings to add to AGENTS.md files.
+
+AGENTS.md files can exist at any directory level, not just the project root. When an agent reads a file, any AGENTS.md in parent directories are automatically loaded into the context of the tool read. Place learnings as close to the relevant code as possible:
+
+- Project-wide learnings → root AGENTS.md
+- Package/module-specific → packages/foo/AGENTS.md
+- Feature-specific → src/auth/AGENTS.md
+
+What counts as a learning (non-obvious discoveries only):
+
+- Hidden relationships between files or modules
+- Execution paths that differ from how code appears
+- Non-obvious configuration, env vars, or flags
+- Debugging breakthroughs when error messages were misleading
+- API/tool quirks and workarounds
+- Build/test commands not in README
+- Architectural decisions and constraints
+- Files that must change together
+
+What NOT to include:
+
+- Obvious facts from documentation
+- Standard language/framework behavior
+- Things already in an AGENTS.md
+- Verbose explanations
+- Session-specific details
+
+Process:
+
+1. Review session for discoveries, errors that took multiple attempts, unexpected connections
+2. Determine scope - what directory does each learning apply to?
+3. Read existing AGENTS.md files at relevant levels
+4. Create or update AGENTS.md at the appropriate level
+5. Keep entries to 1-3 lines per insight
+
+After updating, summarize which AGENTS.md files were created/updated and how many learnings per file.
+
+$ARGUMENTS

package/.rimuru/command/rmslop.md

@@ -0,0 +1,15 @@
+---
+description: Remove AI code slop
+---
+
+Check the diff against dev, and remove all AI generated slop introduced in this branch.
+
+This includes:
+
+- Extra comments that a human wouldn't add or is inconsistent with the rest of the file
+- Extra defensive checks or try/catch blocks that are abnormal for that area of the codebase (especially if called by trusted / validated codepaths)
+- Casts to any to get around type issues
+- Any other style that is inconsistent with the file
+- Unnecessary emoji usage
+
+Report at the end with only a 1-3 sentence summary of what you changed

package/.rimuru/command/spellcheck.md

@@ -0,0 +1,5 @@
+---
+description: spellcheck all markdown file changes
+---
+
+Look at all the unstaged changes to markdown (.md, .mdx) files, pull out the lines that have changed, and check for spelling and grammar errors.

package/.rimuru/command/translate.md

@@ -0,0 +1,14 @@
+---
+description: translate English to other languages
+model: opencode/claude-opus-4-8
+---
+
+run git diff and translate changed english doc and UI copy files to other international languages. Translate all languages in parallel to save time.
+
+Requirements:
+
+- Preserve meaning, intent, tone, and formatting (including Markdown/MDX structure).
+- Preserve all technical terms and artifacts exactly: product/company names, API names, identifiers, code, commands/flags, file paths, URLs, versions, error messages, config keys/values, and anything inside inline code or code blocks.
+- Also preserve every term listed in the Do-Not-Translate glossary below.
+- Also apply locale-specific guidance from `.rimuru/glossary/<locale>.md` when available (for example, `zh-cn.md`).
+- Do not modify fenced code blocks.

package/.rimuru/glossary/README.md

@@ -0,0 +1,63 @@
+# Locale Glossaries
+
+Use this folder for locale-specific translation guidance that supplements `.rimuru/agent/translator.md`.
+
+The global glossary in `translator.md` remains the source of truth for shared do-not-translate terms (commands, code, paths, product names, etc.). These locale files capture community learnings about phrasing and terminology preferences.
+
+## File Naming
+
+- One file per locale
+- Use lowercase locale slugs that match docs locales when possible (for example, `zh-cn.md`, `zh-tw.md`)
+- If only language-level guidance exists, use the language code (for example, `fr.md`)
+- Some repo locale slugs may be aliases/non-BCP47 for consistency (for example, `br` for Brazilian Portuguese / `pt-BR`)
+
+## What To Put In A Locale File
+
+- **Sources**: PRs/issues/discussions that motivated the guidance
+- **Do Not Translate (Locale Additions)**: locale-specific terms or casing decisions
+- **Preferred Terms**: recurring UI/docs words with preferred translations
+- **Guidance**: tone, style, and consistency notes
+- **Avoid** (optional): common literal translations or wording we should avoid
+- If the repo uses a locale alias slug, document the alias in **Guidance** (for example, prose may mention `pt-BR` while config/examples use `br`)
+
+Prefer guidance that is:
+
+- Repeated across multiple docs/screens
+- Easy to apply consistently
+- Backed by a community contribution or review discussion
+
+## Template
+
+```md
+# <locale> Glossary
+
+## Sources
+
+- PR #12345: https://github.com/anomalyco/opencode/pull/12345
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing)
+
+## Preferred Terms
+
+| English | Preferred | Notes     |
+| ------- | --------- | --------- |
+| prompt  | ...       | preferred |
+| session | ...       | preferred |
+
+## Guidance
+
+- Prefer natural phrasing over literal translation
+
+## Avoid
+
+- Avoid ... when ...
+```
+
+## Contribution Notes
+
+- Mark entries as preferred when they may evolve
+- Keep examples short
+- Add or update the `Sources` section whenever you add a new rule
+- Prefer PR-backed guidance over invented term mappings; start with general guidance if no term-level corrections exist yet

package/.rimuru/glossary/ar.md

@@ -0,0 +1,28 @@
+# ar Glossary
+
+## Sources
+
+- PR #9947: https://github.com/anomalyco/opencode/pull/9947
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+No PR-backed term mappings yet. Add entries here when review PRs introduce repeated wording corrections.
+
+## Guidance
+
+- Prefer natural Arabic phrasing over literal translation
+- Keep tone clear and direct in UI labels and docs prose
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+- For RTL text, treat code, commands, and paths as LTR artifacts and keep their character order unchanged
+
+## Avoid
+
+- Avoid translating product and protocol names that are fixed identifiers
+- Avoid mixing multiple Arabic terms for the same recurring UI action once a preferred term is established

package/.rimuru/glossary/br.md

@@ -0,0 +1,34 @@
+# br Glossary
+
+## Sources
+
+- PR #10086: https://github.com/anomalyco/opencode/pull/10086
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Locale code `br` in repo config, code, and paths (repo alias for Brazilian Portuguese)
+
+## Preferred Terms
+
+These are PR-backed locale naming preferences and may evolve.
+
+| English / Context                        | Preferred                      | Notes                                                         |
+| ---------------------------------------- | ------------------------------ | ------------------------------------------------------------- |
+| Brazilian Portuguese (prose locale name) | `pt-BR`                        | Use standard locale naming in prose when helpful              |
+| Repo locale slug (code/config)           | `br`                           | PR #10086 uses `br` for consistency/simplicity                |
+| Browser locale detection                 | `pt`, `pt-br`, `pt-BR` -> `br` | Preserve this mapping in docs/examples about locale detection |
+
+## Guidance
+
+- This file covers Brazilian Portuguese (`pt-BR`), but the repo locale code is `br`
+- Use natural Brazilian Portuguese phrasing over literal translation
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+- Keep repo locale identifiers as implemented in code/config (`br`) even when prose mentions `pt-BR`
+
+## Avoid
+
+- Avoid changing repo locale code references from `br` to `pt-br` in code snippets, paths, or config examples
+- Avoid mixing Portuguese variants when a Brazilian Portuguese form is established

package/.rimuru/glossary/bs.md

@@ -0,0 +1,33 @@
+# bs Glossary
+
+## Sources
+
+- PR #12283: https://github.com/anomalyco/opencode/pull/12283
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+These are PR-backed locale naming preferences and may evolve.
+
+| English / Context                  | Preferred  | Notes                                             |
+| ---------------------------------- | ---------- | ------------------------------------------------- |
+| Bosnian language label (UI)        | `Bosanski` | PR #12283 tested switching language to `Bosanski` |
+| Repo locale slug (code/config)     | `bs`       | Preserve in code, config, paths, and examples     |
+| Browser locale detection (Bosnian) | `bs`       | PR #12283 added `bs` locale auto-detection        |
+
+## Guidance
+
+- Use natural Bosnian phrasing over literal translation
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+- Keep repo locale references as `bs` in code/config, and use `Bosanski` for the user-facing language name when applicable
+
+## Avoid
+
+- Avoid changing repo locale references from `bs` to another slug in code snippets or config examples
+- Avoid translating product and protocol names that are fixed identifiers

package/.rimuru/glossary/da.md

@@ -0,0 +1,27 @@
+# da Glossary
+
+## Sources
+
+- PR #9821: https://github.com/anomalyco/opencode/pull/9821
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+No PR-backed term mappings yet. Add entries here when review PRs introduce repeated wording corrections.
+
+## Guidance
+
+- Prefer natural Danish phrasing over literal translation
+- Keep tone clear and direct in UI labels and docs prose
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+
+## Avoid
+
+- Avoid translating product and protocol names that are fixed identifiers
+- Avoid mixing multiple Danish terms for the same recurring UI action once a preferred term is established

package/.rimuru/glossary/de.md

@@ -0,0 +1,27 @@
+# de Glossary
+
+## Sources
+
+- PR #9817: https://github.com/anomalyco/opencode/pull/9817
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+No PR-backed term mappings yet. Add entries here when review PRs introduce repeated wording corrections.
+
+## Guidance
+
+- Prefer natural German phrasing over literal translation
+- Keep tone clear and direct in UI labels and docs prose
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+
+## Avoid
+
+- Avoid translating product and protocol names that are fixed identifiers
+- Avoid mixing multiple German terms for the same recurring UI action once a preferred term is established

package/.rimuru/glossary/es.md

@@ -0,0 +1,27 @@
+# es Glossary
+
+## Sources
+
+- PR #9817: https://github.com/anomalyco/opencode/pull/9817
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+No PR-backed term mappings yet. Add entries here when review PRs introduce repeated wording corrections.
+
+## Guidance
+
+- Prefer natural Spanish phrasing over literal translation
+- Keep tone clear and direct in UI labels and docs prose
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+
+## Avoid
+
+- Avoid translating product and protocol names that are fixed identifiers
+- Avoid mixing multiple Spanish terms for the same recurring UI action once a preferred term is established

package/.rimuru/glossary/fr.md

@@ -0,0 +1,27 @@
+# fr Glossary
+
+## Sources
+
+- PR #9821: https://github.com/anomalyco/opencode/pull/9821
+
+## Do Not Translate (Locale Additions)
+
+- `OpenCode` (preserve casing in prose; keep `rimuru-ai` only in commands, package names, paths, or code)
+- `OpenCode CLI`
+- `CLI`, `TUI`, `MCP`, `OAuth`
+- Commands, flags, file paths, and code literals (keep exactly as written)
+
+## Preferred Terms
+
+No PR-backed term mappings yet. Add entries here when review PRs introduce repeated wording corrections.
+
+## Guidance
+
+- Prefer natural French phrasing over literal translation
+- Keep tone clear and direct in UI labels and docs prose
+- Preserve technical artifacts exactly: commands, flags, code, URLs, model IDs, and file paths
+
+## Avoid
+
+- Avoid translating product and protocol names that are fixed identifiers
+- Avoid mixing multiple French terms for the same recurring UI action once a preferred term is established