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 ai-driven-dev/framework --skill translategit clone --depth 1 https://github.com/ai-driven-dev/frameworkWrote 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/ai-driven-dev/framework/translate)<a href="https://agentmods.dev/skills/ai-driven-dev/framework/translate"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/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/skills/ai-driven-dev/framework/translate"><img src="https://agentmods.dev/badge/skills/ai-driven-dev/framework/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 | $0.00123 | $0.01015 |
| Opus 5.5 | $0.00049 | $0.00406 |
| Sonnet 5.5 | $0.00025 | $0.00203 |
| Haiku 4.5 | $0.00012 | $0.00102 |
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 1mo 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 — 74 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Translate
translate is the core: it turns the canonical, Claude-format framework source into
target-native content for every tool at once. It reaches two places and no others: tools, its
one outbound context edge, and kernel. Everything it reaches in tools is that context's
declared public surface (contracts.ts, registry.ts, build-contract.ts, and the handful of
capability and port modules listed as public), never an internal file. The whole graph is in
.claude/rules/00-architecture/0-contexts.md.
What goes in
| Concept | Location |
|---|---|
| A transform whose behavior differs by target tool | domain/formats/ |
| The plugin-files-to-installed-files translator | domain/content-translator.ts (PluginContentTranslator) |
| The canonical framework-doc shape | domain/canon.ts |
| The canonical single-plugin shape | domain/plugin-distribution.ts |
| Build targets and modes | domain/build-target.ts |
The aidd translate use-case |
application/translate-source.ts (FrameworkBuildUseCase) |
| A build orchestrator (one per mode, never per tool) | application/strategies/ |
| Schema validation for marketplace/plugin manifests | infrastructure/schema-validator.ts |
A transform used by exactly one tool profile does not belong here — it lives in that profile's
own directory. A transform shared by ≥2 profiles but identical regardless of target lives in
contexts/tools/domain/formats/ instead. What belongs in translate/domain/formats/ is a
transform that is aware of which target it is producing for.
How
PluginContentTranslatortakes one plugin's canonical files and one tool'sAiTool<C>, and calls the tool's ownrewriteContent— it does not reimplement a tool's rewrite logic, it invokes whattoolsdeclared. That function is one-way and has no inverse; thetoolsskill'sreferences/content-rewrite.mdsays why, and names the trap an identity rewrite sets.FrameworkBuildUseCase(aidd translate) reads aToolBuildContractper target and mode fromtools, and dispatches toMarketplaceBuildStrategyorFlatBuildStrategy— both implementBuildOutputStrategyand iterate the six artifact kinds generically, with zero per-tool or per-kind branching. Adding a build target means the target tool declares a contract intools; it never means adding a case here. See thetoolsskill'sreferences/build-contract.md.runtime/wiring/translate.tsderives the"<target>:<mode>"build registry by iterating every registered tool and reading its contract — there is no hand-maintained per-tool row.- Follow the use-case and orchestration rules in
.claude/rules/00-architecture/for the application layer's shape, and the shared-module rule there before promoting a helper used by only one strategy intoshared-plugin-helpers.ts.
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.
- 1mo ago First seen · 74 lines · 123 tokens per session scan A f28b02c1a967
translate is a skill published in the GitHub repository ai-driven-dev/framework (518 stars, last pushed today), licensed MIT. It adds 123 tokens to every session and 1,015 once invoked, about $0.0005 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 2026-09-09.
Other skills, from other repositories
image-generation
Use this skill when the user requests to generate, create, imagine, or visualize images including characters, scenes, products, or any visual content. Supports structured prompts and reference images for guided generation.
podcast-generation
Use this skill when the user requests to generate, create, or produce podcasts from text content. Converts written content into a two-host conversational podcast audio format with natural dialogue.
skill-reviewer
Reviews DeerFlow skill packages for readiness, triggers, safety boundaries, resources, and evidence. Invoke when users ask to audit, grade, or production-check an existing skill.
knowledge-org
A guide to organising large bodies of knowledge so an AI system can navigate relationships, summaries, and layers instead of searching only flat text chunks. It covers tree indexes, knowledge graphs, file-like structures, incremental updates, and long-term memory layouts.
eval-dataset-design
A guide to creating reliable test sets for AI agents. Each evaluation task includes the request, the simulated user's behaviour, a reset starting state, and a success check that can be independently verified.
git-checkpoint
Use git as a safety net - create a checkpoint commit before risky or large changes and roll back cleanly if a change makes things worse. Use before multi-file refactors.