conforme GEMINI.md

CLAUDE.md

Project overview

conforme is a Rust CLI that synchronizes AI coding agent configurations across 14 tools. It reads config from a source tool (Claude Code, Cursor, etc.) or AGENTS.md, and propagates to all other tool-specific config files.

Build & test

cargo build --release
cargo test
cargo clippy -- -D warnings    # lint — MUST pass before pushing
cargo fmt -- --check           # format check
conforme check                 # verify AI configs are in sync (dogfooding)

Architecture

src/
  main.rs           — Entry point, dispatches subcommands
  cli.rs            — CLI arg parsing (clap derive)
  config.rs         — NormalizedConfig, NormalizedRule, NormalizedSkill, NormalizedAgent, NormalizedMcpServer, ActivationMode
  markdown.rs       — AGENTS.md parser (sections → rules via ## Rule: headings)
  frontmatter.rs    — gray_matter wrapper for YAML frontmatter parsing/serialization
  lib.rs            — Library crate re-exports (adapters, config, etc.)
  sync.rs           — Core sync engine: init, sync, check, status, remove commands
  detect.rs         — Tool detection (which tools present in project)
  hash.rs           — SHA-256 content hashing for change detection
  hook.rs           — Git pre-commit hook install/uninstall (like Husky)
  project_config.rs  — .conformerc.toml parser (source, only, exclude, clean options)
  validate.rs        — Config validation (duplicate names, empty content, invalid globs)
  watch.rs           — File watcher for auto-sync (notify + debounce)
  help_ai.rs        — Detailed help about all supported tools and formats
  mcp.rs            — MCP config generation/parsing per tool:
                       - Codex: project `.codex/config.toml`, atomically merged with comment/settings preservation; strict safe parser — merge_codex_mcp_toml / parse_codex_mcp_toml
                       - Standard mcpServers: Claude, Kiro, Amazon Q, Cursor
                       - Roo Code: mcpServers, HTTP uses type "streamable-http" (not "http") — generate_roocode_mcp_json
                       - Continue.dev: mcpServers, HTTP uses type "streamable-http" (bare "http" is rejected) — generate_continue_mcp_json
                       - Claude .mcp.json parsing accepts http/https, sse, streamable-http, and ws transports (all mapped to the HTTP variant)
                       - Copilot: "servers" key (env + headers supported)
                       - Windsurf: mcpServers, no type field, serverUrl for HTTP
                       - OpenCode: "mcp" key merged into opencode.json, type local/remote, command as array, `environment` key
                       - Zed: "context_servers" key
                       - Gemini: mcpServers, no type field, httpUrl for HTTP
                       - Amp: "amp.mcpServers" key merged into .amp/settings.json — build_amp_mcp_object
                       - parse_mcp_json reads back mcpServers / servers / context_servers / amp.mcpServers
                       - OpenCode needs its own inverse (parse_opencode_mcp_object / parse_opencode_agent_object)
  skills.rs         — Skills (SKILL.md) and agents generation per tool; shared read helpers
                       (read_skills_from_dir, read_agents_from_dir, parse_frontmatter_tool_list)
                       used by adapters to round-trip skills/agents on read()
  adapters/
    mod.rs          — AiToolAdapter trait + registry + shared write_if_changed
    claude.rs       — Claude Code: CLAUDE.md + .claude/rules/*.md (paths: frontmatter)
    cursor.rs       — Cursor: .cursor/rules/*.mdc (alwaysApply/globs/description); subagents at .cursor/agents/*.md
    windsurf.rs     — Windsurf: .devin/rules/*.md when .devin/ exists, else .windsurf/rules/*.md (trigger/description/globs)
    copilot.rs      — GitHub Copilot: .github/copilot-instructions.md (applyTo); skills at .github/skills/<name>/SKILL.md
    codex.rs        — OpenAI Codex CLI: reads AGENTS.md natively
    opencode.rs     — OpenCode: reads AGENTS.md natively
    roocode.rs      — Roo Code / Cline: .roo/rules/*.md (plain Markdown)
    gemini.rs       — Gemini CLI: GEMINI.md
    continuedev.rs  — Continue.dev: .continue/rules/*.md (name/globs/alwaysApply)
    zed.rs          — Zed AI: .rules file
    amazonq.rs      — Amazon Q: .amazonq/rules/*.md
    kiro.rs         — Kiro (AWS): .kiro/steering/*.md (inclusion/fileMatchPattern)
    amp.rs          — Amp (Sourcegraph): reads AGENTS.md natively
    deepseek.rs     — DeepSeek Harness (dsh): reads AGENTS.md natively; skills at .dsh/skills/<name>/SKILL.md
tests/
  integration.rs    — CLI integration tests (assert_cmd + tempfile)
  roundtrip.rs      — Write→read round-trip tests for every adapter (rules, skills, agents, MCP)
  error_cases.rs    — Edge cases, MCP sync, agents sync, activation modes
docs/
  providers/        — One doc per supported tool with official URLs, config format, adapter notes