{"passport":{"unfragile":{"@version":"1.0","version":"2026-05","artifact":{"id":"github-mufeedvh--code2prompt","slug":"mufeedvh--code2prompt","name":"code2prompt","type":"cli","url":"https://code2prompt.dev","page_url":"https://unfragile.ai/mufeedvh--code2prompt","categories":["prompt-engineering"],"tags":["ai","chatgpt","claude","cli","command-line","command-line-tool","gpt","llm","prompt","prompt-engineering","prompt-generator","prompt-toolkit","rust"],"pricing":{"model":"open_source","free":true,"starting_price":null},"status":"active","verified":false},"capabilities":[{"id":"github-mufeedvh--code2prompt__cap_0","uri":"capability://data.processing.analysis.gitignore.aware.recursive.directory.traversal.with.intelligent.file.discovery","name":"gitignore-aware recursive directory traversal with intelligent file discovery","description":"Recursively discovers files in a codebase while respecting .gitignore rules through native git integration, building an in-memory file tree that filters out ignored paths before processing. Uses the ignore crate to parse .gitignore patterns and applies them during traversal, avoiding unnecessary I/O on excluded directories. This enables developers to automatically exclude vendor directories, build artifacts, and other non-essential files without manual configuration.","intents":["I want to convert my entire codebase to a prompt without manually specifying which files to include","I need to ensure my .gitignore rules are respected when generating prompts so I don't leak build artifacts or dependencies","I want to recursively discover all relevant source files in a monorepo structure"],"best_for":["developers managing large codebases with complex .gitignore rules","teams working with monorepos where selective file inclusion is critical","engineers building LLM context for code analysis without manual file selection"],"limitations":["Respects only .gitignore at repository root and subdirectories; nested .gitignore files are processed but may have unexpected precedence","Symlinks are followed by default which may cause infinite loops in circular symlink structures","Performance degrades on filesystems with >100k files due to single-threaded traversal"],"requires":["Valid .gitignore file in repository root (optional; traversal works without it)","Read permissions on all directories in traversal path","Rust 1.70+ (for ignore crate compatibility)"],"input_types":["filesystem path (directory)",".gitignore file (parsed automatically)"],"output_types":["in-memory file tree structure","filtered file list ready for processing"],"categories":["data-processing-analysis","file-discovery"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_1","uri":"capability://data.processing.analysis.glob.pattern.based.file.filtering.with.user.override.capability","name":"glob pattern-based file filtering with user override capability","description":"Applies glob patterns to filter files discovered during directory traversal, supporting both inclusion and exclusion patterns with explicit user overrides that take precedence over defaults. The filtering engine evaluates patterns in sequence (include patterns first, then exclusions) and allows users to force-include files that would normally be filtered out via CLI flags or configuration. This enables fine-grained control over which files appear in the final prompt without re-running the entire traversal.","intents":["I want to include only Python files and exclude test files from my prompt","I need to force-include a specific config file that would normally be filtered by .gitignore","I want to exclude all files matching a pattern except for specific exceptions"],"best_for":["developers needing selective file inclusion beyond .gitignore rules","teams with project-specific filtering requirements (e.g., exclude all .test.js files)","engineers building context for domain-specific LLM tasks (e.g., only documentation files)"],"limitations":["Glob patterns are evaluated sequentially; complex pattern interactions may be unintuitive","No support for negative lookahead or advanced regex features; limited to standard glob syntax","Pattern matching is case-sensitive on Unix-like systems and case-insensitive on Windows, which may cause cross-platform inconsistencies"],"requires":["Valid glob pattern syntax (standard shell glob format)","Configuration file or CLI arguments specifying patterns"],"input_types":["glob pattern strings","file list from directory traversal"],"output_types":["filtered file list","inclusion/exclusion metadata per file"],"categories":["data-processing-analysis","filtering-engine"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_10","uri":"capability://memory.knowledge.session.based.state.management.for.multi.step.prompt.generation.workflows","name":"session-based state management for multi-step prompt generation workflows","description":"Implements a Code2PromptSession struct that maintains state across multiple configuration and generation steps, enabling developers to build multi-step workflows (configure filters, select files, generate prompt) without re-traversing the filesystem. Sessions encapsulate the file tree, token map, configuration, and template state, allowing incremental modifications and multiple prompt generations from the same session. This is particularly useful for interactive workflows where users make multiple selections before final output.","intents":["I want to configure my prompt once and generate multiple variations without re-scanning the filesystem","I need to build an interactive workflow where users make selections incrementally","I want to reuse the same file tree and token map for multiple prompt generations"],"best_for":["developers building interactive prompt generation tools","teams creating multi-step workflows that need to preserve state","engineers optimizing for performance by avoiding repeated filesystem traversals"],"limitations":["Session state is in-memory only; not persisted to disk, so closing the application loses all state","Large sessions with >100k files may consume significant memory (estimated 500MB+ for very large codebases)","Session state is not thread-safe; concurrent modifications may cause data corruption","No built-in session serialization; developers must implement custom persistence if needed"],"requires":["Rust 1.70+ for struct and trait support","Sufficient memory to hold file tree and token map in RAM"],"input_types":["codebase path","configuration settings","file selection updates","template modifications"],"output_types":["session object with encapsulated state","generated prompts from session state"],"categories":["memory-knowledge","state-management"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_11","uri":"capability://data.processing.analysis.binary.file.detection.and.safe.handling.with.encoding.options","name":"binary file detection and safe handling with encoding options","description":"Detects binary files using magic byte analysis (checking file headers for known binary signatures) and handles them safely by either skipping them or base64-encoding them for inclusion in prompts. This prevents binary data from corrupting text-based prompts while preserving the option to include binary metadata if needed. The detection uses heuristics (null bytes, non-UTF8 sequences) to identify binary files with high accuracy.","intents":["I want to safely include my entire codebase in a prompt without binary files corrupting the output","I need to detect and skip image files, compiled binaries, and other non-text files automatically","I want to include binary file metadata (size, type) in my prompt without the actual binary data"],"best_for":["developers working with mixed file types (code, images, binaries) in their codebase","teams that want automatic binary detection without manual configuration","engineers building robust prompt generation that handles edge cases"],"limitations":["Binary detection uses heuristics; some edge cases (e.g., UTF-8 text files with binary-like headers) may be misclassified","Base64 encoding increases file size by ~33%; large binary files may significantly increase token count","No support for selective binary inclusion (e.g., include only images); all binaries are handled the same way","Detection adds ~5-10ms overhead per file due to header reading"],"requires":["Read permissions on all files","Sufficient disk I/O performance for header reading"],"input_types":["file path","file content (first 512 bytes for magic byte detection)"],"output_types":["binary classification (true/false)","base64-encoded content (if encoding is enabled)","skip instruction (if binary is excluded)"],"categories":["data-processing-analysis","safety-moderation"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_12","uri":"capability://data.processing.analysis.sorting.and.organization.of.files.in.prompt.output.with.customizable.ordering","name":"sorting and organization of files in prompt output with customizable ordering","description":"Organizes files in the generated prompt using customizable sorting strategies (alphabetical, by size, by modification time, by directory depth) to improve readability and enable LLMs to process related files together. Files can be grouped by directory, sorted within groups, and presented in a hierarchical structure that mirrors the filesystem. This enables developers to control how files appear in the prompt without modifying the underlying file tree.","intents":["I want to organize files by directory so related files appear together in the prompt","I need to sort files by size to put smaller files first for better LLM comprehension","I want to customize the order of files to match my project's logical structure"],"best_for":["developers optimizing prompt structure for LLM comprehension","teams with large codebases that benefit from hierarchical organization","engineers building context engineering tools that need flexible file ordering"],"limitations":["Sorting adds ~10-20ms overhead for large file lists (>10k files)","Custom sorting strategies require code changes; no user-defined sorting rules","Sorting is applied after file selection; cannot be used to filter files","No support for mixed sorting strategies (e.g., sort by directory, then by size within directories)"],"requires":["File metadata (path, size, modification time)","Sorting strategy specification"],"input_types":["file list with metadata","sorting strategy selection"],"output_types":["sorted file list","hierarchical file structure (if grouping is enabled)"],"categories":["data-processing-analysis","organization"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_2","uri":"capability://data.processing.analysis.specialized.file.format.conversion.to.llm.readable.text","name":"specialized file format conversion to llm-readable text","description":"Processes specialized file types (CSV, JSONL, Jupyter notebooks, binary files) into structured text representations suitable for LLM consumption, with format-specific handlers that preserve semantic information. CSV files are converted to markdown tables, JSONL is pretty-printed with indentation, Jupyter notebooks extract code cells and markdown, and binary files are detected and either skipped or base64-encoded. Each processor is modular and can be extended to support additional formats without modifying the core pipeline.","intents":["I want to include CSV data files in my prompt as readable tables instead of raw comma-separated values","I need to extract code and documentation from Jupyter notebooks for LLM analysis","I want to detect and safely handle binary files so they don't corrupt my prompt output","I need to include JSONL log files in my prompt with proper formatting"],"best_for":["data scientists including notebooks and CSV files in LLM context","teams with mixed file types (code, data, documentation) in their codebase","engineers building context for analysis tasks that require structured data"],"limitations":["CSV conversion to markdown tables may produce very wide tables for files with 50+ columns, reducing readability","Jupyter notebook conversion extracts only code and markdown cells; output cells and metadata are discarded","Binary file detection uses magic bytes; some edge cases (e.g., text files with binary-like headers) may be misclassified","JSONL pretty-printing adds whitespace that increases token count; no option for compact output"],"requires":["csv crate for CSV parsing","serde_json for JSON/JSONL handling","jupyter-format compatible notebook structure"],"input_types":["CSV files","JSONL files","Jupyter notebook files (.ipynb)","Binary files (any format)"],"output_types":["markdown-formatted tables (CSV)","pretty-printed JSON (JSONL)","extracted code and markdown (notebooks)","base64-encoded or skipped (binary)"],"categories":["data-processing-analysis","format-conversion"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_3","uri":"capability://data.processing.analysis.token.counting.and.context.window.management.with.per.file.accounting","name":"token counting and context window management with per-file accounting","description":"Counts tokens using tiktoken-rs (OpenAI's tokenizer) to track context usage and prevent exceeding LLM context window limits, providing per-file token counts and cumulative totals. The system tracks tokens for file content, templates, and metadata separately, allowing developers to see exactly which files consume the most tokens and make informed decisions about inclusion. A token map is maintained during processing to enable interactive token-aware file selection in the TUI.","intents":["I want to know how many tokens my prompt will consume before sending it to an LLM","I need to fit my codebase into a 4k context window and want to see which files use the most tokens","I want to compare token usage across different file types to optimize my prompt"],"best_for":["developers optimizing prompts for cost-sensitive LLM APIs (GPT-3.5, Claude)","teams working with context-limited models (4k, 8k token windows)","engineers building interactive tools that need real-time token feedback"],"limitations":["Token counts are approximate for non-OpenAI models; tiktoken-rs uses OpenAI's cl100k_base encoding which may differ from Claude, Llama, or other tokenizers by 5-15%","Token counting adds ~50-100ms overhead per file due to tokenizer initialization","No support for custom tokenizers; developers must use OpenAI's encoding or estimate manually","Token map is built in-memory; very large codebases (>1M tokens) may consume significant RAM"],"requires":["tiktoken-rs crate (included in dependencies)","OpenAI cl100k_base tokenizer model (loaded on first use)"],"input_types":["file content (text)","template strings","metadata (file paths, sizes)"],"output_types":["per-file token counts","cumulative token total","token map (file -> token count mapping)","token statistics (min, max, average per file)"],"categories":["data-processing-analysis","token-management"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_4","uri":"capability://data.processing.analysis.git.aware.context.generation.with.diff.log.and.branch.comparison","name":"git-aware context generation with diff, log, and branch comparison","description":"Integrates with git to include version control information in prompts, supporting git diffs (staged/unstaged changes), commit logs, and branch comparisons. Developers can include recent commits, changes between branches, or the current diff to provide LLMs with context about recent modifications. This is implemented via git2-rs bindings that query the repository's git objects directly, avoiding shell invocations and enabling cross-platform compatibility.","intents":["I want to include recent git commits in my prompt so the LLM understands recent changes","I need to show the diff between my current branch and main to provide context for code review","I want to include staged changes in my prompt for an LLM to review before committing"],"best_for":["developers using LLMs for code review and understanding recent changes","teams working on feature branches who want to provide context about divergence from main","engineers building AI-assisted commit message generation or change summarization"],"limitations":["Git integration requires a valid .git directory; works only with git repositories, not other VCS","Diff output can be very large for binary files or large refactorings; no built-in truncation","Commit log retrieval is limited to the current branch; cross-branch history requires manual branch specification","Large repositories with deep history may experience slow git object traversal"],"requires":["git2-rs crate (included in dependencies)","Valid .git directory in repository root","Git repository initialized with at least one commit"],"input_types":["git repository path","branch names (for comparisons)","commit count (for log depth)"],"output_types":["unified diff format (git diff output)","commit log with messages and metadata","branch comparison (commits on current branch not on target)"],"categories":["data-processing-analysis","version-control-integration"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_5","uri":"capability://text.generation.language.template.based.prompt.generation.with.variable.substitution.and.conditional.blocks","name":"template-based prompt generation with variable substitution and conditional blocks","description":"Generates prompts using Handlebars-style templates that support variable substitution, conditional blocks, and iteration over file lists. Templates are rendered with context variables (codebase structure, file contents, git information) and can include conditional sections (e.g., 'if has_git_info'). This enables developers to create reusable prompt templates that adapt to different codebases without manual editing, with built-in templates for common scenarios (code review, documentation generation, etc.).","intents":["I want to create a reusable prompt template that works with any codebase","I need to conditionally include git information only if the repository has git history","I want to generate different prompts for different tasks (code review vs. documentation) using the same codebase"],"best_for":["teams building prompt engineering workflows with multiple templates","developers creating reusable LLM context for different tasks","engineers building prompt generation as part of a larger pipeline"],"limitations":["Template syntax is Handlebars-based; developers must learn Handlebars syntax for complex templates","No support for custom template functions; limited to built-in helpers (if, each, etc.)","Template rendering adds ~10-20ms overhead per prompt; not suitable for real-time streaming","Large templates with many variables may be difficult to debug if rendering fails"],"requires":["handlebars crate (included in dependencies)","Valid Handlebars template syntax","Context variables populated from codebase analysis"],"input_types":["Handlebars template string","context object (codebase structure, file contents, metadata)"],"output_types":["rendered prompt string","validation errors if template syntax is invalid"],"categories":["text-generation-language","template-system"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_6","uri":"capability://automation.workflow.interactive.tui.based.file.selection.with.real.time.token.feedback","name":"interactive tui-based file selection with real-time token feedback","description":"Provides a terminal user interface (TUI) built with ratatui using an Elm/Redux architecture for state management, enabling interactive file selection with real-time token counting feedback. Users can navigate a file tree, toggle files on/off, see token impact of each selection, and preview the generated prompt before output. The TUI maintains a Redux-style state machine where user actions (select file, toggle, navigate) dispatch events that update the model and re-render the view.","intents":["I want to interactively select which files to include in my prompt without using CLI flags","I need to see token counts update in real-time as I toggle files on and off","I want to preview my prompt before generating it to ensure it's correct"],"best_for":["developers who prefer interactive workflows over command-line flags","teams building context engineering as an interactive process","engineers exploring different file combinations to optimize prompts"],"limitations":["TUI is terminal-only; requires a terminal emulator with support for ANSI escape codes","Performance degrades with >10k files due to full tree rendering on each state change","No mouse support; navigation is keyboard-only (arrow keys, vim keys)","TUI state is not persisted; closing the application loses all selections"],"requires":["ratatui crate (included in dependencies)","Terminal with ANSI escape code support (most modern terminals)","Rust 1.70+ for ratatui compatibility"],"input_types":["file tree from directory traversal","token map from token counting","template configuration"],"output_types":["user-selected file list","rendered prompt preview","output destination (stdout, file, clipboard)"],"categories":["automation-workflow","user-interface"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_7","uri":"capability://tool.use.integration.multi.interface.api.exposure.via.cli.python.sdk.and.mcp.server","name":"multi-interface api exposure via cli, python sdk, and mcp server","description":"Exposes the core code2prompt_core library through three distinct interfaces: a CLI binary (via clap argument parsing), Python bindings (via PyO3), and an MCP (Model Context Protocol) server for agentic applications. Each interface wraps the core library with domain-specific concerns (argument parsing for CLI, Python type conversion for SDK, MCP message handling for agents). This architecture allows the same business logic to be consumed by shell scripts, Python applications, and AI agents without duplication.","intents":["I want to use code2prompt from the command line in my shell scripts","I want to integrate code2prompt into my Python application without subprocess calls","I want to expose code2prompt as an MCP server so my AI agent can use it"],"best_for":["developers building multi-interface tools that need to support CLI, SDK, and agent access","teams with mixed tech stacks (shell, Python, AI agents) that need unified access","engineers building prompt engineering platforms that need programmatic and interactive interfaces"],"limitations":["Python SDK requires PyO3 compilation; binary wheels are provided but custom builds may be needed for unsupported platforms","MCP server requires MCP client implementation; not all LLM frameworks support MCP yet","Each interface has slightly different error handling and output formatting; behavior may vary across interfaces","Maintaining three interfaces increases testing burden; bugs may exist in one interface but not others"],"requires":["For CLI: Rust 1.70+, clap crate","For Python SDK: Python 3.8+, PyO3 crate, maturin for building wheels","For MCP: MCP-compatible client (e.g., Claude Desktop, custom agent framework)"],"input_types":["CLI arguments (for CLI interface)","Python function arguments (for SDK)","MCP protocol messages (for MCP server)"],"output_types":["stdout/file output (CLI)","Python objects/dictionaries (SDK)","MCP protocol responses (MCP server)"],"categories":["tool-use-integration","api-exposure"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_8","uri":"capability://automation.workflow.configuration.file.based.settings.with.yaml.toml.support.and.cli.override","name":"configuration file-based settings with yaml/toml support and cli override","description":"Supports configuration files (YAML or TOML format) that specify default settings for file filtering, templates, output formats, and token limits, with CLI arguments taking precedence over file-based settings. Configuration files are loaded from standard locations (.code2prompt.yaml, code2prompt.toml) and can be overridden per-invocation via CLI flags. This enables teams to establish project-wide defaults while allowing individual developers to customize behavior without modifying shared configuration.","intents":["I want to set project-wide defaults for file filtering so all team members use the same rules","I need to override a configuration setting for a single run without modifying the config file","I want to version control my prompt generation settings as part of my repository"],"best_for":["teams establishing consistent prompt generation practices across projects","developers who want to avoid repeating CLI flags for common workflows","engineers building prompt generation as part of CI/CD pipelines"],"limitations":["Configuration file discovery is limited to standard locations; no support for custom config paths","YAML and TOML syntax errors produce cryptic parser errors; no validation or helpful error messages","Configuration merging is shallow; nested settings cannot be partially overridden","No support for environment variable substitution in config files"],"requires":["serde crate for serialization/deserialization","serde_yaml or toml crate depending on format","Valid YAML or TOML syntax in configuration file"],"input_types":["YAML or TOML configuration file","CLI arguments (for overrides)"],"output_types":["merged configuration object","validation errors if syntax is invalid"],"categories":["automation-workflow","configuration-management"],"confidence":0.5,"matches":0,"success_rate":0},{"id":"github-mufeedvh--code2prompt__cap_9","uri":"capability://automation.workflow.output.routing.to.multiple.destinations.with.format.selection","name":"output routing to multiple destinations with format selection","description":"Routes generated prompts to multiple output destinations (stdout, file, clipboard) with support for different output formats (plain text, JSON, markdown). The output system abstracts destination handling so the same prompt can be written to different targets without code changes. Clipboard output uses the arboard crate for cross-platform compatibility, and file output supports automatic path resolution and directory creation.","intents":["I want to copy my prompt directly to clipboard so I can paste it into ChatGPT","I need to save my prompt to a file for version control and review","I want to output my prompt as JSON so I can parse it programmatically"],"best_for":["developers who want flexible output options without code changes","teams building prompt generation pipelines that need multiple output formats","engineers integrating code2prompt into larger workflows"],"limitations":["Clipboard output requires X11 on Linux; may fail on headless servers or WSL without additional setup","Large prompts (>10MB) may exceed clipboard size limits on some systems","JSON output adds overhead for serialization; not suitable for streaming large prompts","File output does not support atomic writes; partial writes may occur if process crashes"],"requires":["arboard crate for clipboard access","Write permissions on output file path (for file output)","X11 or equivalent clipboard manager (for clipboard output on Linux)"],"input_types":["rendered prompt string","output destination specification (stdout, file path, clipboard)","output format selection (text, json, markdown)"],"output_types":["prompt written to stdout","prompt written to file","prompt copied to clipboard","prompt serialized as JSON"],"categories":["automation-workflow","output-handling"],"confidence":0.5,"matches":0,"success_rate":0}],"trust":{"score":50,"verified":false,"data_access_risk":"high","permissions":["Valid .gitignore file in repository root (optional; traversal works without it)","Read permissions on all directories in traversal path","Rust 1.70+ (for ignore crate compatibility)","Valid glob pattern syntax (standard shell glob format)","Configuration file or CLI arguments specifying patterns","Rust 1.70+ for struct and trait support","Sufficient memory to hold file tree and token map in RAM","Read permissions on all files","Sufficient disk I/O performance for header reading","File metadata (path, size, modification time)"],"failure_modes":["Respects only .gitignore at repository root and subdirectories; nested .gitignore files are processed but may have unexpected precedence","Symlinks are followed by default which may cause infinite loops in circular symlink structures","Performance degrades on filesystems with >100k files due to single-threaded traversal","Glob patterns are evaluated sequentially; complex pattern interactions may be unintuitive","No support for negative lookahead or advanced regex features; limited to standard glob syntax","Pattern matching is case-sensitive on Unix-like systems and case-insensitive on Windows, which may cause cross-platform inconsistencies","Session state is in-memory only; not persisted to disk, so closing the application loses all state","Large sessions with >100k files may consume significant memory (estimated 500MB+ for very large codebases)","Session state is not thread-safe; concurrent modifications may cause data corruption","No built-in session serialization; developers must implement custom persistence if needed","builder identity is not verified yet","no observed match outcomes yet"],"rank_breakdown":{"adoption":0.610631454741096,"quality":0.5,"ecosystem":0.6000000000000001,"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":"2026-05-24T12:16:22.062Z","last_scraped_at":"2026-05-03T13:59:50.673Z","last_commit":"2026-04-14T04:36:59Z"},"community":{"stars":7323,"forks":421,"weekly_downloads":null,"model_downloads":null,"model_likes":null}},"distribution":{"claim_url":"https://unfragile.ai/submit?claim=mufeedvh--code2prompt","compare_url":"https://unfragile.ai/compare?artifact=mufeedvh--code2prompt"}},"signature":"vGSbl57XZ7uzRCsrAXeNVf2L+59hF8IklSDTK8gzKhNWSn5RkLA6m7daO3EtRLyjfHHyDmcKkiW3XM4xIgp7AQ==","signedAt":"2026-06-22T03:40:50.920Z","signedBy":"unfragile.ai","version":1},"_links":{"self":"https://unfragile.ai/api/v1/passport/mufeedvh--code2prompt","artifact":"https://unfragile.ai/mufeedvh--code2prompt","verify":"https://unfragile.ai/api/v1/verify?slug=mufeedvh--code2prompt","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"}}