How long does the integration take?

Change one base URL in an OpenAI-compatible client, or install the Python or TypeScript SDK; the quickstart routes a first request in a few minutes.

Will this lock us into another vendor?

No. The router is Apache-2.0 open source, your provider keys stay yours, and the API is OpenAI-compatible, so leaving is a change of base URL.

What happens when a provider fails?

The router falls back to the next model your policy allows and records the fallback in the trace, so an outage costs a retry, not an incident.

gsd-map-codebase - Prompt - OpenSmartRoute

Name: gsd-map-codebase
Author: mileschintw

Prompt file imported from mileschintw/rust-lancedb-graphrag (.claude/commands/gsd-map-codebase.md). Fill in {{arguments}} before use. Copyright stays with the author.

Each mapper agent explores a focus area and writes documents directly to .planning/codebase/. The orchestrator only receives confirmations, keeping context usage minimal.

Output: .planning/codebase/ folder with 7 structured documents about the codebase state.

<execution_context> @/Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/map-codebase.md </execution_context>

Parse the first token of {{arguments}}:

If it is --fast: strip the flag, then read and execute /Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/scan.md (passing remaining args including optional --focus). Load it on demand here — it is deliberately not in <execution_context>, so the common full-map path does not pay for it.
If it is --query: strip the flag, run the intel workflow (passing remaining args as the subcommand).
Otherwise: pass all of {{arguments}} as focus area to the map-codebase workflow.

Load project state if exists: Check for .planning/STATE.md - loads context if project already initialized

This command can run:

Via /gsd-onboard for first-time brownfield setup - creates codebase map first
After /gsd-new-project (greenfield codebases) - updates codebase map as code evolves
Anytime to refresh codebase understanding

<when_to_use> Use map-codebase for:

Brownfield projects before initialization (understand existing code first)
Refreshing codebase map after significant changes
Refreshing or deepening an onboarded codebase map
Before major refactoring (understand current state)
When STATE.md references outdated codebase info

Skip map-codebase for:

Greenfield projects with no code yet (nothing to map)
Trivial codebases (<5 files) </when_to_use>

<success_criteria>

.planning/codebase/ directory created
All 7 codebase documents written by mapper agents
Documents follow template structure
Parallel agents completed without errors
User knows next steps </success_criteria>

Install gsd-map-codebase and it becomes one more candidate the router can pick - when it fits.

A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.

<objective> Analyze existing codebase using parallel gsd-codebase-mapper agents to produce structured codebase documents. Each mapper agent explores a focus area and **writes documents directly** to `.planning/codebase/`. The orchestrator only receives confirmations, keeping context usage minimal. Output: .planning/codebase/ folder with 7 structured documents about the codebase state. </objective> <execution_context> @/Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/map-codebase.md </execution_context> <flags> - **--fast**: Lightweight scan mode — spawns one mapper agent instead of four. Accepts an optional `--focus` value: `tech`, `arch`, `quality`, `concerns`, or `tech+arch` (default). Faster and lower-context than the full map. - **--query**: Codebase intelligence query mode. Sub-commands: `query <term>`, `status`, `diff`, `refresh`. Requires intel to be enabled in config (`intel.enabled: true`). Runs inline for query/status/diff; spawns an agent for refresh. - **(no flag)**: Full parallel map — spawns 4 mapper agents to produce all 7 codebase documents. </flags> <context> Arguments: {{arguments}} Parse the first token of {{arguments}}: - If it is `--fast`: strip the flag, then read and execute `/Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/scan.md` (passing remaining args including optional --focus). Load it on demand here — it is deliberately not in `<execution_context>`, so the common full-map path does not pay for it. - If it is `--query`: strip the flag, run the intel workflow (passing remaining args as the subcommand). - Otherwise: pass all of {{arguments}} as focus area to the map-codebase workflow. **Load project state if exists:** Check for .planning/STATE.md - loads context if project already initialized **This command can run:** - Via /gsd-onboard for first-time brownfield setup - creates codebase map first - After /gsd-new-project (greenfield codebases) - updates codebase map as code evolves - Anytime to refresh codebase understanding </context> <when_to_use> **Use map-codebase for:** - Brownfield projects before initialization (understand existing code first) - Refreshing codebase map after significant changes - Refreshing or deepening an onboarded codebase map - Before major refactoring (understand current state) - When STATE.md references outdated codebase info **Skip map-codebase for:** - Greenfield projects with no code yet (nothing to map) - Trivial codebases (<5 files) </when_to_use> <process> 1. Check if .planning/codebase/ already exists (offer to refresh or skip) 2. Create .planning/codebase/ directory structure 3. Spawn 4 parallel gsd-codebase-mapper agents: - Agent 1: tech focus → writes STACK.md, INTEGRATIONS.md - Agent 2: arch focus → writes ARCHITECTURE.md, STRUCTURE.md - Agent 3: quality focus → writes CONVENTIONS.md, TESTING.md - Agent 4: concerns focus → writes CONCERNS.md 4. Wait for agents to complete, collect confirmations (NOT document contents) 5. Verify all 7 documents exist with line counts 6. Commit codebase map 7. Offer next steps (typically: /gsd-onboard, /gsd-new-project, or /gsd-plan-phase) </process> <success_criteria> - [ ] .planning/codebase/ directory created - [ ] All 7 codebase documents written by mapper agents - [ ] Documents follow template structure - [ ] Parallel agents completed without errors - [ ] User knows next steps </success_criteria>

{ "prompt": "<objective>\nAnalyze existing codebase using parallel gsd-codebase-mapper agents to produce structured codebase documents.\n\nEach mapper agent explores a focus area and **writes documents directly** to `.planning/codebase/`. The orchestrator only receives confirmations, keeping context usage minimal.\n\nOutput: .planning/codebase/ folder with 7 structured documents about the codebase state.\n</objective>\n\n<execution_context>\n@/Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/map-codebase.md\n</execution_context>\n\n<flags>\n- **--fast**: Lightweight scan mode — spawns one mapper agent instead of four. Accepts an optional `--focus` value: `tech`, `arch`, `quality`, `concerns`, or `tech+arch` (default). Faster and lower-context than the full map.\n- **--query**: Codebase intelligence query mode. Sub-commands: `query <term>`, `status`, `diff`, `refresh`. Requires intel to be enabled in config (`intel.enabled: true`). Runs inline for query/status/diff; spawns an agent for refresh.\n- **(no flag)**: Full parallel map — spawns 4 mapper agents to produce all 7 codebase documents.\n</flags>\n\n<context>\nArguments: {{arguments}}\n\nParse the first token of {{arguments}}:\n- If it is `--fast`: strip the flag, then read and execute `/Users/mileschintw/Desktop/repos/rust-lancedb-graphrag/.claude/gsd-core/workflows/scan.md` (passing remaining args including optional --focus). Load it on demand here — it is deliberately not in `<execution_context>`, so the common full-map path does not pay for it.\n- If it is `--query`: strip the flag, run the intel workflow (passing remaining args as the subcommand).\n- Otherwise: pass all of {{arguments}} as focus area to the map-codebase workflow.\n\n**Load project state if exists:**\nCheck for .planning/STATE.md - loads context if project already initialized\n\n**This command can run:**\n- Via /gsd-onboard for first-time brownfield setup - creates codebase map first\n- After /gsd-new-project (greenfield codebases) - updates codebase map as code evolves\n- Anytime to refresh codebase understanding\n</context>\n\n<when_to_use>\n**Use map-codebase for:**\n- Brownfield projects before initialization (understand existing code first)\n- Refreshing codebase map after significant changes\n- Refreshing or deepening an onboarded codebase map\n- Before major refactoring (understand current state)\n- When STATE.md references outdated codebase info\n\n**Skip map-codebase for:**\n- Greenfield projects with no code yet (nothing to map)\n- Trivial codebases (<5 files)\n</when_to_use>\n\n<process>\n1. Check if .planning/codebase/ already exists (offer to refresh or skip)\n2. Create .planning/codebase/ directory structure\n3. Spawn 4 parallel gsd-codebase-mapper agents:\n - Agent 1: tech focus → writes STACK.md, INTEGRATIONS.md\n - Agent 2: arch focus → writes ARCHITECTURE.md, STRUCTURE.md\n - Agent 3: quality focus → writes CONVENTIONS.md, TESTING.md\n - Agent 4: concerns focus → writes CONCERNS.md\n4. Wait for agents to complete, collect confirmations (NOT document contents)\n5. Verify all 7 documents exist with line counts\n6. Commit codebase map\n7. Offer next steps (typically: /gsd-onboard, /gsd-new-project, or /gsd-plan-phase)\n</process>\n\n<success_criteria>\n- [ ] .planning/codebase/ directory created\n- [ ] All 7 codebase documents written by mapper agents\n- [ ] Documents follow template structure\n- [ ] Parallel agents completed without errors\n- [ ] User knows next steps\n</success_criteria>", "variables": [ "arguments" ], "notes": "Analyze codebase with parallel mapper agents to produce .planning/codebase/ documents Tools: Read, Bash, Glob, Grep, Write, Agent. Arguments: [--fast [--focus tech|arch|quality|concerns]] [--query <term>|status|diff|refresh] [area].", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/mileschintw/rust-lancedb-graphrag", "path": ".claude/commands/gsd-map-codebase.md", "ref": "7c6cc2ad9e5bfb0c9388d505a213f2bab752a439", "url": "https://github.com/mileschintw/rust-lancedb-graphrag/blob/7c6cc2ad9e5bfb0c9388d505a213f2bab752a439/.claude/commands/gsd-map-codebase.md", "key": "mileschintw/rust-lancedb-graphrag/.claude/commands/gsd-map-codebase.md" } } }

gsd-map-codebase

About

Install gsd-map-codebase and it becomes one more candidate the router can pick - when it fits.

What it costs to adopt - in engineering time.

One base URL

No vendor lock-in

Failover built in

Use it

Manifest

Reviews