feat(installer): multi-target — Claude Code, Cursor, Codex CLI, opencode by colbymchenry · Pull Request #162 · colbymchenry/codegraph

colbymchenry · 2026-05-17T23:25:37Z

Closes #137.

The runtime MCP server is already agent-agnostic (stdio). Only the installer was Claude-locked. This refactor makes codegraph install write per-agent MCP config + instructions for any combination of supported agents.

Based on andreinknv/codegraph@c5165e4 — credited as commit author. Thanks @andreinknv for the substantive draft.

Summary

4 agent targets behind a new AgentTarget interface: Claude Code, Cursor, Codex CLI, opencode. Adding a 5th (Continue, Zed, Windsurf, …) is one file in src/installer/targets/ + one line in registry.ts.
New CLI flags: --target, --location, --yes, --no-permissions, --print-config. Bare codegraph install still works — interactive prompt now multi-selects detected agents.
Hand-rolled TOML serializer for Codex (src/installer/targets/toml.ts), scoped to the [mcp_servers.codegraph] block only. Siblings + [[array_of_tables]] preserved verbatim. No new dependency.
Backwards compat: every export from the old config-writer.ts is preserved as a @deprecated shim. Existing Claude installs are byte-identical on disk; detect() reports alreadyConfigured: true, re-running is a no-op.
Uninstall now loops ALL_TARGETS.uninstall('global') — a user with our [mcp_servers.codegraph] block in ~/.codex/config.toml will have only that block removed (not the whole file).

CLI

codegraph install                                   # interactive multi-select
codegraph install --yes                             # auto-detect, install global
codegraph install --target=cursor,claude --yes     # explicit list
codegraph install --target=auto --location=local   # detected, project-local
codegraph install --target=none                    # skip agent writes entirely
codegraph install --print-config codex             # dump snippet, no writes

Tests

566/566 pass locally. +47 new tests in __tests__/installer-targets.test.ts:

Parameterized contract across all 4 targets × supported locations: install → second-run-unchanged, sibling preservation, uninstall reverses install, printConfig writes nothing.
Codex partial-state recovery, locked-block contract on the codegraph table, full TOML serializer suite.
Registry: getTarget, resolveTargetFlag (auto/all/none/csv).

One assertion in __tests__/installer.test.ts relaxed: byte-identical re-runs now return unchanged instead of updated. The surrounding-custom-content contract is untouched.

Test plan

npm run build clean
npm test 566/566 pass
Codex (hand): codegraph install --target=codex --yes writes ~/.codex/config.toml + ~/.codex/AGENTS.md; restart Codex CLI; verify MCP tools surface
Codex print-config: codegraph install --print-config codex dumps the TOML snippet only, no file writes
Codex idempotency: second codegraph install --target=codex --yes reports unchanged on both files
Codex sibling preservation: pre-add an unrelated [mcp_servers.other] entry, re-install, confirm the sibling is untouched
Codex uninstall: npm uninstall -g @colbymchenry/codegraph strips the [mcp_servers.codegraph] block + AGENTS.md section, leaves siblings + custom AGENTS.md content intact
Claude regression: existing Claude install runs a no-op on re-install (covered by tests, but worth a smoke check)
Cursor / opencode: not hand-tested — covered by parameterized contract tests only. Future user reports welcome.

Conflicts resolved during cherry-pick

src/bin/codegraph.ts — install command applied manually (the fork's line numbers were ~300 lines off ours).
src/installer/index.ts — two LLM-setup hunks skipped; that code is fork-only and not on our main.

🤖 Generated with Claude Code

Closes the Claude-locked installer behind issue #137. The runtime MCP server was already agent-agnostic (stdio); only the installer was locked. After this refactor, `codegraph install` can write per-agent MCP config + instructions for any combination of supported agents. ## What ships Four agent targets, each implementing the new `AgentTarget` interface: - **Claude Code** — `~/.claude.json`, `~/.claude/settings.json`, `~/.claude/CLAUDE.md` (or local equivalents). Behavior preserved from the original installer; existing installs upgrade in place. - **Cursor** — `~/.cursor/mcp.json` (g) or `./.cursor/mcp.json` (l) + project-local `./.cursor/rules/codegraph.mdc`. - **Codex CLI** — `~/.codex/config.toml` with `[mcp_servers.codegraph]` + `~/.codex/AGENTS.md`. Global only. Hand-rolled TOML serializer scoped to the table we own — siblings + array-of-tables preserved. - **opencode** — `~/.config/opencode/opencode.json` (XDG) or `./opencode.json`. Adding a 5th agent is a new file in `src/installer/targets/` plus one entry in `registry.ts`. ## CLI changes ``` codegraph install # interactive multi-select codegraph install --yes # auto-detect, install global codegraph install --target=cursor,claude --yes # explicit list codegraph install --target=auto --location=local # detected, project-local codegraph install --target=none # skip agent writes entirely codegraph install --print-config codex # dump snippet, no writes ``` ## Backwards compat Every export from the old `config-writer.ts` (`writeMcpConfig`, `writePermissions`, `writeClaudeMd`, `hasMcpConfig`, `hasPermissions`, `hasClaudeMdSection`) is preserved as a `@deprecated` shim that delegates to per-file helpers in `targets/claude.ts`. Existing Claude users see byte-identical on-disk layout — `detect()` reports `alreadyConfigured: true`, re-running is a no-op. ## Tests +47 new tests in `__tests__/installer-targets.test.ts`: - Parameterized contract test across all 4 targets × supported locations (install → unchanged on re-run, sibling preservation, uninstall reverses install, printConfig writes nothing). - Codex partial-state recovery, locked-block contract for the codegraph table, full TOML serializer suite. - Registry: getTarget, resolveTargetFlag (auto/all/none/csv). `__tests__/installer.test.ts` relaxed one assertion: the new code returns `unchanged` for byte-identical re-runs instead of `updated`; the surrounding-custom-content contract is unchanged. ## Uninstall behavior change `bin/uninstall.ts` now loops `ALL_TARGETS.uninstall('global')` on `npm uninstall -g`. A user who manually configured `~/.codex/config.toml` with our block will have only that block removed on package uninstall — we only touch the dotted-key table we own. Based on andreinknv/codegraph@c5165e4. Issue #137. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Builds the current branch and `npm link`s it as the global `codegraph` binary. `--undo` unlinks and reinstalls the published version. Mirrors the style of scripts/release.sh. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Reorders runInstallerWithOptions so the multi-select for agents (Claude / Cursor / Codex / opencode) is step 1 — before the global-npm-install confirm and before the location prompt. Bare `npx @colbymchenry/codegraph` now opens with "Which agents should CodeGraph configure?", which is the answer most users want first. Side effects of the reorder: - Early exit if zero targets selected — skips global-install and location prompts entirely, exits with "nothing to do." - Multiselect labels drop the per-location "will skip" hint (location isn't known yet) and replace it with a static "global only" badge for targets like Codex that have no project-local config concept. - If every selected target is global-only, the location prompt is skipped and global is forced (no point asking). - Detection probes the user-provided location if known via flag, else 'global' as the most common default — labels are a hint about what's installed locally, not load-bearing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Two prompts both said "global" but meant different things — users read them as duplicates. Renamed for clarity: - Step 2 (npm install -g): "Install codegraph globally?" → "Install the codegraph CLI on your PATH? (Required so agents can launch the MCP server)". Spinner messages match. - Step 3 (config location): "Where would you like to install?" with "Global"/"Local" → "Apply agent configs to all your projects, or just this one?" with "All projects" (~/.claude, ~/.cursor, etc.) / "Just this project" (./.claude, ./.cursor, etc.). - All-global-only fallback: "Using global install" → "Writing user-wide configs (selected agents have no project-local config)." Underlying `Location` values ('global' / 'local') unchanged; only the UI strings shift, so no test or flag breakage. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Cursor launches MCP-server subprocesses with cwd != workspace root, AND does not pass rootUri or workspaceFolders in the MCP initialize call. The codegraph MCP server's process.cwd() fallback misses the workspace's .codegraph/ and reports "not initialized" on every tool call. Codex and Claude don't have this issue (Codex launches with cwd=workspace, Claude passes rootUri). Fix: inject `--path` into the args we write for Cursor. - local install (./.cursor/mcp.json): hardcode the absolute project path — known at install time. - global install (~/.cursor/mcp.json): use `${workspaceFolder}` so Cursor expands it per-workspace. One global config now drives every project the user opens, without per-project re-install. No test breakage — the parameterized contract tests check idempotency / sibling preservation, not the exact args content. File-header comment documents the rationale so the next person doesn't strip the arg as boilerplate. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

Closes the global-Cursor UX gap: `~/.cursor/mcp.json` registers the MCP server, but Cursor's agent only learns to *prefer* codegraph over native grep when it sees `.cursor/rules/codegraph.mdc` — a project-local file that global install can't write. Previously the user had to re-run `codegraph install --target=cursor --location=local` for every new project. Now `codegraph init` does it automatically. ## What changed - New optional `AgentTarget.wireProjectSurfaces()` returning a WriteResult of project-local files to drop. Most targets omit it (their global config is complete). Cursor implements it to write the rules file. - New `wireProjectSurfacesForGlobalAgents()` orchestrator in installer/index.ts — iterates ALL_TARGETS, detects which are configured globally, calls their wireProjectSurfaces, returns what was written. - `codegraph init` calls the orchestrator in both branches: - Fresh init: write surfaces after CodeGraph.init succeeds. - Already-initialized re-init: write surfaces too, so re-running `init` is the documented recovery path for a project missing its rules file. ## Steady-state UX 1. Once, ever: `codegraph install` (writes global agent configs) 2. Per project: `codegraph init -i` (builds the index + auto-wires project-local agent surfaces — currently Cursor's rules file) No new tests — wireProjectSurfaces delegates to writeRulesEntry, which is already covered by the parameterized contract tests. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

The old template was inherited from the Claude-only era and prescribed "ALWAYS spawn an Explore agent" — a Claude Code-specific concept (subagents via the Task tool). When Cursor's agent read this it had no Explore agent to spawn, got confused, and fell back to native grep/read even for structural queries the codegraph MCP tools answer in one call. This rewrite: - Frames each tool by the question it answers (search vs callers vs impact vs context vs explore vs node vs files vs status). - Tells the agent explicitly to TRUST codegraph results and not re-verify them with grep — the over-grep-after-codegraph behavior was the main symptom we saw on Cursor. - Reframes "spawn Explore agent" as an OPTIONAL pattern for harnesses that support parallel subagents — Claude Code still gets the hint, Cursor / Codex / opencode just skip it. - Trims the "if not initialized" section to one prescriptive line. Same marker delimiters (``) so existing installs upgrade in place via the marker-based section swap. No test changes needed — the parameterized contract tests check marker placement + sibling preservation, not the literal body. Effective surfaces: ~/.claude/CLAUDE.md (Claude), .cursor/rules/ codegraph.mdc (Cursor, project-local), ~/.codex/AGENTS.md (Codex). Users get the new copy by re-running `codegraph install` for global writes, or `codegraph init` for Cursor's project rules. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

- Tagline now reads "Supercharge Claude Code, Cursor & Codex" instead of Claude-only — multi-agent support is what the PR is about, the README should say so above the fold. - New badge row (Claude Code / Cursor / Codex CLI / opencode) in the same shields.io style as the OS row. - Install-flow bullets reordered to match the actual prompt order (agent picker first, then PATH install, then location). - `codegraph init -i` step now mentions that init wires up project-local agent surfaces (Cursor rules file etc.) so global install works in every project without a re-run. - Agent-agnostic phrasing in the closing line ("your agent" not "Claude Code"). Headline-level brand decision left intentionally in this PR — the existing Claude-only positioning predates multi-agent support. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…ode (colbymchenry#162) * feat(installer): multi-target — Claude Code, Cursor, Codex CLI, opencode Closes the Claude-locked installer behind issue colbymchenry#137. The runtime MCP server was already agent-agnostic (stdio); only the installer was locked. After this refactor, `codegraph install` can write per-agent MCP config + instructions for any combination of supported agents. ## What ships Four agent targets, each implementing the new `AgentTarget` interface: - **Claude Code** — `~/.claude.json`, `~/.claude/settings.json`, `~/.claude/CLAUDE.md` (or local equivalents). Behavior preserved from the original installer; existing installs upgrade in place. - **Cursor** — `~/.cursor/mcp.json` (g) or `./.cursor/mcp.json` (l) + project-local `./.cursor/rules/codegraph.mdc`. - **Codex CLI** — `~/.codex/config.toml` with `[mcp_servers.codegraph]` + `~/.codex/AGENTS.md`. Global only. Hand-rolled TOML serializer scoped to the table we own — siblings + array-of-tables preserved. - **opencode** — `~/.config/opencode/opencode.json` (XDG) or `./opencode.json`. Adding a 5th agent is a new file in `src/installer/targets/` plus one entry in `registry.ts`. ## CLI changes ``` codegraph install # interactive multi-select codegraph install --yes # auto-detect, install global codegraph install --target=cursor,claude --yes # explicit list codegraph install --target=auto --location=local # detected, project-local codegraph install --target=none # skip agent writes entirely codegraph install --print-config codex # dump snippet, no writes ``` ## Backwards compat Every export from the old `config-writer.ts` (`writeMcpConfig`, `writePermissions`, `writeClaudeMd`, `hasMcpConfig`, `hasPermissions`, `hasClaudeMdSection`) is preserved as a `@deprecated` shim that delegates to per-file helpers in `targets/claude.ts`. Existing Claude users see byte-identical on-disk layout — `detect()` reports `alreadyConfigured: true`, re-running is a no-op. ## Tests +47 new tests in `__tests__/installer-targets.test.ts`: - Parameterized contract test across all 4 targets × supported locations (install → unchanged on re-run, sibling preservation, uninstall reverses install, printConfig writes nothing). - Codex partial-state recovery, locked-block contract for the codegraph table, full TOML serializer suite. - Registry: getTarget, resolveTargetFlag (auto/all/none/csv). `__tests__/installer.test.ts` relaxed one assertion: the new code returns `unchanged` for byte-identical re-runs instead of `updated`; the surrounding-custom-content contract is unchanged. ## Uninstall behavior change `bin/uninstall.ts` now loops `ALL_TARGETS.uninstall('global')` on `npm uninstall -g`. A user who manually configured `~/.codex/config.toml` with our block will have only that block removed on package uninstall — we only touch the dotted-key table we own. Based on andreinknv/codegraph@c5165e4. Issue colbymchenry#137. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * chore(scripts): add local-install.sh for hands-on branch testing Builds the current branch and `npm link`s it as the global `codegraph` binary. `--undo` unlinks and reinstalls the published version. Mirrors the style of scripts/release.sh. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(installer): move agent picker to the first prompt Reorders runInstallerWithOptions so the multi-select for agents (Claude / Cursor / Codex / opencode) is step 1 — before the global-npm-install confirm and before the location prompt. Bare `npx @colbymchenry/codegraph` now opens with "Which agents should CodeGraph configure?", which is the answer most users want first. Side effects of the reorder: - Early exit if zero targets selected — skips global-install and location prompts entirely, exits with "nothing to do." - Multiselect labels drop the per-location "will skip" hint (location isn't known yet) and replace it with a static "global only" badge for targets like Codex that have no project-local config concept. - If every selected target is global-only, the location prompt is skipped and global is forced (no point asking). - Detection probes the user-provided location if known via flag, else 'global' as the most common default — labels are a hint about what's installed locally, not load-bearing. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(installer): disambiguate "global" wording in install prompts Two prompts both said "global" but meant different things — users read them as duplicates. Renamed for clarity: - Step 2 (npm install -g): "Install codegraph globally?" → "Install the codegraph CLI on your PATH? (Required so agents can launch the MCP server)". Spinner messages match. - Step 3 (config location): "Where would you like to install?" with "Global"/"Local" → "Apply agent configs to all your projects, or just this one?" with "All projects" (~/.claude, ~/.cursor, etc.) / "Just this project" (./.claude, ./.cursor, etc.). - All-global-only fallback: "Using global install" → "Writing user-wide configs (selected agents have no project-local config)." Underlying `Location` values ('global' / 'local') unchanged; only the UI strings shift, so no test or flag breakage. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * fix(installer/cursor): inject --path so workspace-aware queries work Cursor launches MCP-server subprocesses with cwd != workspace root, AND does not pass rootUri or workspaceFolders in the MCP initialize call. The codegraph MCP server's process.cwd() fallback misses the workspace's .codegraph/ and reports "not initialized" on every tool call. Codex and Claude don't have this issue (Codex launches with cwd=workspace, Claude passes rootUri). Fix: inject `--path` into the args we write for Cursor. - local install (./.cursor/mcp.json): hardcode the absolute project path — known at install time. - global install (~/.cursor/mcp.json): use `${workspaceFolder}` so Cursor expands it per-workspace. One global config now drives every project the user opens, without per-project re-install. No test breakage — the parameterized contract tests check idempotency / sibling preservation, not the exact args content. File-header comment documents the rationale so the next person doesn't strip the arg as boilerplate. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(init): auto-wire project-local agent surfaces Closes the global-Cursor UX gap: `~/.cursor/mcp.json` registers the MCP server, but Cursor's agent only learns to *prefer* codegraph over native grep when it sees `.cursor/rules/codegraph.mdc` — a project-local file that global install can't write. Previously the user had to re-run `codegraph install --target=cursor --location=local` for every new project. Now `codegraph init` does it automatically. ## What changed - New optional `AgentTarget.wireProjectSurfaces()` returning a WriteResult of project-local files to drop. Most targets omit it (their global config is complete). Cursor implements it to write the rules file. - New `wireProjectSurfacesForGlobalAgents()` orchestrator in installer/index.ts — iterates ALL_TARGETS, detects which are configured globally, calls their wireProjectSurfaces, returns what was written. - `codegraph init` calls the orchestrator in both branches: - Fresh init: write surfaces after CodeGraph.init succeeds. - Already-initialized re-init: write surfaces too, so re-running `init` is the documented recovery path for a project missing its rules file. ## Steady-state UX 1. Once, ever: `codegraph install` (writes global agent configs) 2. Per project: `codegraph init -i` (builds the index + auto-wires project-local agent surfaces — currently Cursor's rules file) No new tests — wireProjectSurfaces delegates to writeRulesEntry, which is already covered by the parameterized contract tests. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * feat(installer): agent-agnostic instructions template The old template was inherited from the Claude-only era and prescribed "ALWAYS spawn an Explore agent" — a Claude Code-specific concept (subagents via the Task tool). When Cursor's agent read this it had no Explore agent to spawn, got confused, and fell back to native grep/read even for structural queries the codegraph MCP tools answer in one call. This rewrite: - Frames each tool by the question it answers (search vs callers vs impact vs context vs explore vs node vs files vs status). - Tells the agent explicitly to TRUST codegraph results and not re-verify them with grep — the over-grep-after-codegraph behavior was the main symptom we saw on Cursor. - Reframes "spawn Explore agent" as an OPTIONAL pattern for harnesses that support parallel subagents — Claude Code still gets the hint, Cursor / Codex / opencode just skip it. - Trims the "if not initialized" section to one prescriptive line. Same marker delimiters (``) so existing installs upgrade in place via the marker-based section swap. No test changes needed — the parameterized contract tests check marker placement + sibling preservation, not the literal body. Effective surfaces: ~/.claude/CLAUDE.md (Claude), .cursor/rules/ codegraph.mdc (Cursor, project-local), ~/.codex/AGENTS.md (Codex). Users get the new copy by re-running `codegraph install` for global writes, or `codegraph init` for Cursor's project rules. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> * docs(readme): reflect multi-agent support at the top + accurate flow - Tagline now reads "Supercharge Claude Code, Cursor & Codex" instead of Claude-only — multi-agent support is what the PR is about, the README should say so above the fold. - New badge row (Claude Code / Cursor / Codex CLI / opencode) in the same shields.io style as the OS row. - Install-flow bullets reordered to match the actual prompt order (agent picker first, then PATH install, then location). - `codegraph init -i` step now mentions that init wires up project-local agent surfaces (Cursor rules file etc.) so global install works in every project without a re-run. - Agent-agnostic phrasing in the closing line ("your agent" not "Claude Code"). Headline-level brand decision left intentionally in this PR — the existing Claude-only positioning predates multi-agent support. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com> --------- Co-authored-by: andreinknv <andrei.nknv@outlook.com> Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

andreinknv and others added 8 commits May 17, 2026 18:23

colbymchenry merged commit a447e1d into main May 18, 2026

colbymchenry deleted the feat/multi-agent-installer branch May 18, 2026 00:26

This was referenced May 18, 2026

Codex / Cursor support #137

Closed

Does codegraph is compatible with other harness tools like opencode? If yes then README.md has no instructions for this. #79

Closed

NgoQuocViet2001 mentioned this pull request May 20, 2026

fix(installer): use opencode config dir on Windows #192

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(installer): multi-target — Claude Code, Cursor, Codex CLI, opencode#162

feat(installer): multi-target — Claude Code, Cursor, Codex CLI, opencode#162
colbymchenry merged 8 commits into
mainfrom
feat/multi-agent-installer

colbymchenry commented May 17, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Conversation

colbymchenry commented May 17, 2026

Summary

CLI

Tests

Test plan

Conflicts resolved during cherry-pick

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants