{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-yamadashy--repomix","slug":"yamadashy--repomix","name":"repomix","type":"cli","url":"https://repomix.com","page_url":"https://unfragile.ai/yamadashy--repomix","categories":["data-pipelines"],"tags":["ai","anthropic","artificial-intelligence","chatbot","chatgpt","claude","deepseek","developer-tools","gemini","genai","generative-ai","gpt","javascript","language-model","llama","llm","mcp","nodejs","openai","typescript"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-yamadashy--repomix__cap_0","uri":"capability://data.processing.analysis.multi.format.codebase.packaging.with.llm.optimized.output","name":"multi-format codebase packaging with llm-optimized output","description":"Orchestrates a six-phase pipeline (discovery via glob patterns and .gitignore rules, parallel file collection, security validation via Secretlint, transformation with Tree-sitter compression, template-based formatting, and tiktoken-based token counting) to pack entire repositories into single files in XML, Markdown, JSON, or Plain Text formats. Uses worker-based parallel processing to handle large codebases efficiently while maintaining structural awareness through AST parsing rather than naive concatenation.","intents":["I need to feed my entire codebase to Claude or ChatGPT as a single context window","I want to understand token consumption before sending code to an LLM","I need to package a repository for analysis without manually selecting files","I want to strip comments and compress code to fit within LLM context limits"],"best_for":["developers integrating codebases with LLM-based code analysis tools","teams using Claude or ChatGPT for full-codebase refactoring tasks","engineers building AI-assisted code review workflows"],"limitations":["Tree-sitter compression only works for supported languages (40+ languages); unsupported languages fall back to plain text","Large repositories (>100MB) may require significant memory during parallel processing phase","Token counting via tiktoken is approximate and may differ from actual LLM tokenization by 2-5%","Remote repository processing requires network access and cloning overhead (~5-30s depending on repo size)"],"requires":["Node.js 18+","Git installed (for local and remote repository operations)","Disk space equal to ~2-3x the repository size (for cloning and output generation)"],"input_types":["local filesystem paths","remote Git repository URLs","glob patterns for file selection",".gitignore rules for exclusion"],"output_types":["XML (structured with metadata)","Markdown (human-readable with code blocks)","JSON (machine-parseable with statistics)","Plain Text (minimal formatting)"],"categories":["data-processing-analysis","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_1","uri":"capability://data.processing.analysis.configuration.driven.file.selection.and.filtering","name":"configuration-driven file selection and filtering","description":"Implements a declarative configuration system (via .repomixrc.json or CLI flags) that supports glob patterns, .gitignore integration, language-specific filters, and file size limits. The configuration loader merges CLI arguments with file-based config using a precedence hierarchy, allowing users to define complex inclusion/exclusion rules without modifying code. Supports both positive patterns (include) and negative patterns (exclude) with gitignore-style semantics.","intents":["I want to exclude node_modules, .git, and build artifacts from the packaged output","I need to include only Python and JavaScript files in my codebase package","I want to set a maximum file size limit to avoid packaging large binary or generated files","I need to reuse the same filtering rules across multiple packaging operations"],"best_for":["teams with large monorepos needing selective codebase packaging","developers building CI/CD pipelines with consistent filtering rules","organizations with security policies requiring exclusion of sensitive file patterns"],"limitations":["Configuration merging follows a fixed precedence (CLI > .repomixrc.json > defaults); no custom precedence rules","Glob patterns use standard micromatch syntax; advanced regex patterns not supported",".gitignore integration only respects rules in the repository root, not nested .gitignore files","File size limits are applied per-file; no aggregate size budgeting across the output"],"requires":["Node.js 18+",".repomixrc.json file in repository root (optional; CLI flags can override)","Valid glob pattern syntax (micromatch compatible)"],"input_types":["JSON configuration file (.repomixrc.json)","CLI flag arguments (--include, --exclude, --maxFileSize)",".gitignore rules from repository"],"output_types":["filtered file list","inclusion/exclusion statistics","configuration validation errors"],"categories":["data-processing-analysis","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_10","uri":"capability://tool.use.integration.web.platform.with.interactive.try.it.interface","name":"web platform with interactive try-it interface","description":"Provides a browser-based interface for testing Repomix functionality without local installation. The web platform includes an interactive try-it interface where users can input repository URLs or paste code, configure packaging options, and preview output in real-time. Server-side API handles repository cloning and processing, with results streamed back to the browser. Supports multi-language documentation and localized UI.","intents":["I want to try Repomix without installing it locally","I need to test packaging options before committing to a configuration","I want to package a repository and preview the output in my browser","I need to understand Repomix capabilities through interactive examples"],"best_for":["developers exploring Repomix for the first time","teams evaluating Repomix before adopting it in their workflow","non-technical users who prefer web interfaces over CLI tools"],"limitations":["Web platform processes repositories on a shared server; large repositories may be rate-limited or rejected","Server-side processing adds latency (~5-30s) compared to local CLI execution","Output preview is limited to browser rendering; very large outputs may cause browser performance issues","No persistent storage of packaged outputs; results are discarded after session ends"],"requires":["Web browser with JavaScript enabled","Network access to the Repomix web platform","Optional: Git repository URL or code to paste"],"input_types":["Git repository URL","pasted code snippets","configuration options (format, filters, compression)"],"output_types":["packaged output preview in browser","downloadable output file","configuration export"],"categories":["tool-use-integration","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_11","uri":"capability://tool.use.integration.github.browser.extension.for.repository.packaging","name":"github browser extension for repository packaging","description":"Provides a browser extension that integrates Repomix directly into GitHub's web interface. Users can click a button on any GitHub repository page to package the repository without leaving GitHub. The extension communicates with the Repomix web platform API to handle processing, and provides options to download or copy the packaged output. Supports both public and private repositories (with authentication).","intents":["I want to package a GitHub repository without navigating away from GitHub","I need to quickly package a repository I'm browsing for analysis with an LLM","I want to package a private repository directly from GitHub with my authentication","I need to integrate repository packaging into my GitHub browsing workflow"],"best_for":["developers who spend significant time on GitHub and want quick packaging access","teams reviewing open-source repositories for code analysis","engineers who want to minimize context switching between GitHub and other tools"],"limitations":["Extension requires browser installation and permissions; not available on all browsers","Private repository packaging requires GitHub authentication; extension must be authorized to access private repos","Large repository packaging may timeout due to browser extension execution limits","Extension UI is limited by browser extension sandbox; advanced configuration options may not be available"],"requires":["Chrome, Firefox, or other Chromium-based browser","Browser extension installed from official store","GitHub account (for private repository access)","Network access to Repomix web platform"],"input_types":["GitHub repository URL (extracted from current page)","optional configuration options (format, filters)"],"output_types":["packaged output file (downloadable)","copy-to-clipboard option","configuration export"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_12","uri":"capability://automation.workflow.github.actions.integration.for.ci.cd.packaging","name":"github actions integration for ci/cd packaging","description":"Provides a GitHub Action that enables automated repository packaging as part of CI/CD workflows. The action can be triggered on push, pull request, or schedule events, packaging the repository and uploading results as artifacts or committing them to the repository. Supports configuration via action inputs (format, filters, compression options) and environment variables. Integrates with GitHub's artifact storage and release systems.","intents":["I want to automatically package my repository on every commit for analysis","I need to generate packaged codebase snapshots as CI/CD artifacts","I want to commit packaged output to my repository for version control","I need to integrate repository packaging into my GitHub Actions workflow"],"best_for":["teams using GitHub Actions for CI/CD automation","projects that need regular codebase snapshots for analysis or archival","organizations building AI-assisted development workflows integrated with GitHub"],"limitations":["GitHub Actions execution time limits (6 hours per job) may affect very large repositories","Artifact storage is limited (5GB default); large packaged outputs may exceed limits","Action runs on GitHub-hosted runners; no access to local development environment","Configuration is limited to action inputs and environment variables; no interactive configuration"],"requires":["GitHub repository with Actions enabled","GitHub Actions workflow file (.github/workflows/*.yml)","Optional: GitHub token for artifact upload or repository commits"],"input_types":["action inputs (format, filters, compression options)","environment variables","trigger events (push, pull request, schedule)"],"output_types":["packaged output artifact (uploaded to GitHub)","committed output file (if configured)","workflow logs and status"],"categories":["automation-workflow","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_2","uri":"capability://tool.use.integration.remote.repository.cloning.and.processing","name":"remote repository cloning and processing","description":"Enables packaging of remote Git repositories by cloning them to a temporary directory, processing the cloned files through the standard pipeline, and cleaning up temporary storage. Supports both HTTPS and SSH Git URLs with automatic credential handling. The remoteAction() function orchestrates cloning, validation, and cleanup with error recovery for network failures or invalid repository URLs.","intents":["I want to package a GitHub repository without cloning it locally first","I need to analyze a private repository's codebase with an LLM without exposing credentials","I want to package a specific branch or commit of a remote repository","I need to integrate remote repository packaging into a CI/CD pipeline"],"best_for":["developers analyzing open-source repositories for code review or refactoring","CI/CD pipelines that need to package dependencies or related repositories","teams using Repomix in GitHub Actions for automated codebase analysis"],"limitations":["Cloning large repositories (>500MB) may timeout or consume significant bandwidth; no shallow clone option","SSH authentication requires SSH keys configured on the host machine; HTTPS requires Git credentials","Temporary directory cleanup may fail on Windows if files are locked; manual cleanup may be required","No support for monorepo subdirectory cloning; entire repository is always cloned"],"requires":["Node.js 18+","Git installed and configured","Network access to the remote repository","Valid Git URL (HTTPS or SSH format)","SSH keys or Git credentials configured (for private repositories)"],"input_types":["Git repository URL (HTTPS or SSH)","optional branch or commit reference","optional authentication credentials"],"output_types":["packaged codebase file (XML, Markdown, JSON, or Plain Text)","clone operation logs","error messages for network or authentication failures"],"categories":["tool-use-integration","automation-workflow"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_3","uri":"capability://tool.use.integration.model.context.protocol.mcp.server.integration","name":"model context protocol (mcp) server integration","description":"Exposes Repomix functionality as an MCP server that integrates directly with AI assistants like Claude. Implements MCP tools for packing repositories and retrieving packaged content, allowing AI assistants to invoke Repomix operations within their native tool-calling interface. The MCP server mode runs as a separate process that communicates with the AI assistant via JSON-RPC over stdio, enabling seamless integration without CLI invocation overhead.","intents":["I want Claude to package my repository and analyze it without leaving the conversation","I need to give an AI assistant the ability to package different repositories on-demand","I want to integrate Repomix as a native tool in my AI assistant's toolkit","I need to automate codebase packaging within an agentic workflow"],"best_for":["developers using Claude or other MCP-compatible AI assistants","teams building AI agents that need to analyze multiple repositories","organizations integrating Repomix into custom AI assistant platforms"],"limitations":["MCP server requires explicit configuration in the AI assistant's settings; not auto-discovered","Tool invocations are subject to the AI assistant's rate limiting and timeout policies","Large repository packaging operations may exceed the AI assistant's tool execution timeout (typically 30-60s)","MCP server runs as a separate process; no built-in process management or auto-restart on failure"],"requires":["Node.js 18+","MCP-compatible AI assistant (Claude, or custom MCP client)","MCP server configuration in the AI assistant's settings","Network access to the local MCP server (typically localhost:port)"],"input_types":["repository path (local or remote URL)","configuration options (format, filters, compression settings)","MCP tool invocation parameters"],"output_types":["packaged codebase content","operation status and metadata","error messages for invalid inputs or processing failures"],"categories":["tool-use-integration","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_4","uri":"capability://code.generation.editing.tree.sitter.based.code.compression.and.comment.stripping","name":"tree-sitter-based code compression and comment stripping","description":"Leverages Tree-sitter AST parsing to intelligently strip comments and compress code structure across 40+ programming languages. For each supported language, the system parses source code into an abstract syntax tree, identifies comment nodes, removes them while preserving code semantics, and optionally adds line numbers for reference. Unsupported languages fall back to regex-based comment stripping. This approach reduces token consumption by 20-40% compared to naive concatenation while maintaining code structure.","intents":["I want to reduce token consumption when packaging my codebase for LLM analysis","I need to strip comments from code while preserving all functional logic","I want to add line numbers to packaged code for easier reference in LLM responses","I need language-aware code compression that understands syntax, not just regex patterns"],"best_for":["developers working with large codebases that exceed LLM context limits","teams optimizing token consumption for cost-sensitive LLM APIs","engineers building code analysis tools that require semantic preservation"],"limitations":["Tree-sitter parsing adds ~50-200ms per file depending on file size and language complexity","Only 40+ languages have native Tree-sitter grammar support; unsupported languages use regex fallback","Comment stripping may remove important documentation comments (e.g., docstrings); no semantic awareness of comment importance","Line number addition increases output size by ~5-10%; trade-off between compression and reference utility"],"requires":["Node.js 18+","Tree-sitter library and language grammars (bundled with Repomix)","Source code in a supported language (40+ languages) or fallback to regex-based stripping"],"input_types":["source code files in supported languages","configuration flags (--stripComments, --addLineNumbers)"],"output_types":["compressed source code with comments removed","line number mappings (optional)","token count estimates"],"categories":["code-generation-editing","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_5","uri":"capability://data.processing.analysis.tiktoken.based.token.counting.and.metrics","name":"tiktoken-based token counting and metrics","description":"Integrates OpenAI's tiktoken library to calculate accurate token counts for packaged output before sending to LLMs. Provides per-file and aggregate token statistics, allowing users to understand context window consumption and optimize packaging parameters. The metrics system tracks compression ratios, file counts, and estimated costs for different LLM providers based on token counts.","intents":["I want to know how many tokens my packaged codebase will consume before sending it to an LLM","I need to estimate the cost of processing my codebase with a paid LLM API","I want to understand which files contribute most to token consumption","I need to optimize my codebase packaging to fit within a specific token budget"],"best_for":["developers using paid LLM APIs (OpenAI, Anthropic) who need cost estimation","teams optimizing codebase packaging for context window constraints","engineers building tools that require accurate token consumption metrics"],"limitations":["tiktoken token counts are approximate and may differ from actual LLM tokenization by 2-5%","Different LLM providers (OpenAI, Anthropic, Claude) use different tokenizers; tiktoken is OpenAI-specific","Token counting adds ~100-500ms overhead depending on output size","Cost estimation requires manual configuration of per-token pricing for different LLM providers"],"requires":["Node.js 18+","tiktoken library (bundled with Repomix)","Optional: LLM provider pricing configuration for cost estimation"],"input_types":["packaged codebase content (any format)","LLM provider configuration (optional, for cost estimation)"],"output_types":["total token count","per-file token counts","compression ratio statistics","estimated cost (if pricing configured)"],"categories":["data-processing-analysis","memory-knowledge"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_6","uri":"capability://safety.moderation.security.scanning.with.secretlint.integration","name":"security scanning with secretlint integration","description":"Integrates Secretlint into the transformation pipeline to detect and prevent accidental exposure of secrets (API keys, credentials, tokens) in packaged output. Scans files during the transformation phase before output generation, flagging files containing detected secrets and optionally blocking packaging or redacting sensitive content. Supports configurable secret patterns and multiple secret detection rules.","intents":["I want to ensure my packaged codebase doesn't accidentally expose API keys or credentials","I need to scan for secrets before sending code to an LLM","I want to redact or block files containing detected secrets","I need to enforce security policies that prevent secret leakage in AI-assisted workflows"],"best_for":["teams with security policies requiring secret scanning before external processing","developers using LLMs for code analysis who need to prevent credential exposure","organizations building secure AI-assisted development workflows"],"limitations":["Secretlint detection is pattern-based and may have false positives/negatives depending on rule configuration","Secret redaction may break code functionality if secrets are embedded in logic (e.g., hardcoded API endpoints)","Scanning adds ~50-200ms overhead depending on file count and size","Custom secret patterns require manual Secretlint configuration; no built-in pattern learning"],"requires":["Node.js 18+","Secretlint library (bundled with Repomix)","Optional: custom Secretlint configuration for organization-specific secret patterns"],"input_types":["source code files","Secretlint configuration (optional)"],"output_types":["secret detection results (file path, line number, secret type)","redacted or blocked files","security scan report"],"categories":["safety-moderation","data-processing-analysis"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_7","uri":"capability://data.processing.analysis.multi.format.output.generation.with.template.system","name":"multi-format output generation with template system","description":"Implements a template-based output generation system supporting XML, Markdown, JSON, and Plain Text formats. Each format uses language-specific templates that structure packaged content with metadata (file paths, line counts, language), making output optimized for different consumption patterns. The builder pattern allows programmatic output construction with format-specific optimizations, while templates enable user-customizable output structure.","intents":["I want to package my codebase in a format that my LLM prefers (XML, Markdown, JSON, or plain text)","I need structured metadata (file paths, line counts) alongside code content","I want to customize the output format for specific LLM or tool requirements","I need to generate output that's both machine-parseable and human-readable"],"best_for":["developers integrating Repomix output with different LLM APIs or tools","teams with specific output format requirements for downstream processing","organizations building custom AI-assisted workflows with format-specific optimizations"],"limitations":["Custom templates require understanding of template syntax; no visual template builder","XML and JSON formats add ~10-20% overhead compared to plain text due to structural markup","Markdown format assumes code blocks are supported; may not render correctly in all contexts","Template customization is per-invocation; no persistent template storage or versioning"],"requires":["Node.js 18+","Valid template syntax for custom templates (Handlebars or similar)","Output format selection (--format xml|markdown|json|plaintext)"],"input_types":["packaged codebase content","format selection flag","optional custom template"],"output_types":["XML file with structured metadata","Markdown file with code blocks","JSON file with hierarchical structure","Plain text file with minimal formatting"],"categories":["data-processing-analysis","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_8","uri":"capability://planning.reasoning.agent.skills.generation.for.ai.assistants","name":"agent skills generation for ai assistants","description":"Generates structured skill definitions that enable AI assistants to understand and invoke Repomix capabilities. Produces skill descriptions, parameter schemas, and usage examples in formats compatible with AI assistant frameworks. The system introspects Repomix configuration and capabilities to generate accurate skill definitions without manual specification, enabling AI agents to discover and use Repomix features dynamically.","intents":["I want to give an AI agent the ability to package repositories without hardcoding Repomix invocations","I need to generate skill definitions that describe Repomix capabilities to an AI assistant","I want an AI agent to understand what parameters Repomix accepts and what outputs it produces","I need to enable dynamic skill discovery so AI agents can adapt to Repomix updates"],"best_for":["developers building AI agents that need to invoke Repomix dynamically","teams integrating Repomix into custom AI assistant platforms","organizations building agentic workflows that require flexible tool invocation"],"limitations":["Skill generation requires introspection of Repomix configuration; changes to config schema require skill regeneration","Generated skills are static snapshots; no real-time skill updates if Repomix capabilities change","Skill definitions are framework-specific; different AI assistant platforms require different skill formats","Parameter validation in generated skills may not match actual Repomix validation logic exactly"],"requires":["Node.js 18+","Repomix configuration schema (introspected from code)","Target AI assistant framework (Claude, custom MCP client, etc.)"],"input_types":["Repomix configuration schema","target skill format specification"],"output_types":["skill definition JSON","parameter schema","usage examples","capability documentation"],"categories":["planning-reasoning","tool-use-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-yamadashy--repomix__cap_9","uri":"capability://automation.workflow.cli.with.interactive.spinner.and.progress.feedback","name":"cli with interactive spinner and progress feedback","description":"Provides a command-line interface with real-time progress feedback via animated spinners and status messages. The CLI runner (cliRun.ts) orchestrates the packaging pipeline with visual feedback at each stage (discovery, collection, validation, transformation, formatting, metrics). Supports both verbose and quiet output modes, with structured logging for debugging and error reporting.","intents":["I want visual feedback while Repomix is processing my repository","I need to understand which stage of packaging is currently running","I want to see detailed logs for debugging packaging failures","I need quiet output for CI/CD pipelines without progress spam"],"best_for":["developers using Repomix interactively from the command line","teams integrating Repomix into CI/CD pipelines with progress monitoring","engineers debugging packaging issues with detailed logs"],"limitations":["Spinner animation may not render correctly in non-TTY environments (CI/CD logs); requires --quiet flag","Progress feedback is stage-level, not file-level; no per-file progress for large repositories","Verbose logging adds overhead (~5-10% slower execution); not recommended for performance-critical workflows","Spinner animation uses terminal control codes that may not work on all terminal emulators"],"requires":["Node.js 18+","TTY terminal for spinner animation (optional; falls back to text output)","CLI invocation via bin/repomix.cjs or npm/Homebrew installation"],"input_types":["CLI arguments and flags","configuration file (.repomixrc.json)"],"output_types":["progress feedback (spinners, status messages)","packaged output file","error messages and logs"],"categories":["automation-workflow","text-generation-language"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":53,"verified":false,"data_access_risk":"high","permissions":["Node.js 18+","Git installed (for local and remote repository operations)","Disk space equal to ~2-3x the repository size (for cloning and output generation)",".repomixrc.json file in repository root (optional; CLI flags can override)","Valid glob pattern syntax (micromatch compatible)","Web browser with JavaScript enabled","Network access to the Repomix web platform","Optional: Git repository URL or code to paste","Chrome, Firefox, or other Chromium-based browser","Browser extension installed from official store"],"failure_modes":["Tree-sitter compression only works for supported languages (40+ languages); unsupported languages fall back to plain text","Large repositories (>100MB) may require significant memory during parallel processing phase","Token counting via tiktoken is approximate and may differ from actual LLM tokenization by 2-5%","Remote repository processing requires network access and cloning overhead (~5-30s depending on repo size)","Configuration merging follows a fixed precedence (CLI > .repomixrc.json > defaults); no custom precedence rules","Glob patterns use standard micromatch syntax; advanced regex patterns not supported",".gitignore integration only respects rules in the repository root, not nested .gitignore files","File size limits are applied per-file; no aggregate size budgeting across the output","Web platform processes repositories on a shared server; large repositories may be rate-limited or rejected","Server-side processing adds latency (~5-30s) compared to local CLI execution","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.7293903284441537,"quality":0.5,"ecosystem":0.65,"match_graph":0.25,"freshness":0.75,"weights":{"adoption":0.25,"quality":0.25,"ecosystem":0.1,"match_graph":0.28,"freshness":0.12}},"observed_outcomes":{"matches":0,"success_rate":0,"avg_confidence":0,"top_intents":[],"last_matched_at":null},"maintenance":{"status":"active","updated_at":"2026-05-24T12:16:22.064Z","last_scraped_at":"2026-05-03T13:58:21.997Z","last_commit":"2026-05-03T13:57:52Z"},"community":{"stars":24271,"forks":1198,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=yamadashy--repomix","compare_url":"https://unfragile.ai/compare?artifact=yamadashy--repomix"}},"signature":"2OYsSSSUBhgIX5wlB2bqZLyobTK7W7R7GHb+uPLcEKuPKPzfhi7BSHNbspsi52M+GRrs7k7EUZoLYaQ0fLQ2Bw==","signedAt":"2026-06-20T05:43:26.965Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/yamadashy--repomix","artifact":"https://unfragile.ai/yamadashy--repomix","verify":"https://unfragile.ai/api/v1/verify?slug=yamadashy--repomix","publicKey":"https://unfragile.ai/api/v1/trust-passport-public-key","spec":"https://unfragile.ai/trust","schema":"https://unfragile.ai/schema.json","docs":"https://unfragile.ai/docs"}}