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:thread - Prompt - OpenSmartRoute

Name: gsd:thread
Author: AnishMulay

Prompt file imported from AnishMulay/LibM (.claude/commands/gsd/thread.md). Fill in {{arguments}}, {{THREAD_NAME}}, {{SLUG}}, {{ARGUMENTS}} before use. Copyright stays with the author.

Parse {{arguments}} to determine mode:

<mode_list> If no arguments or {{arguments}} is empty:

List all threads:

ls .planning/threads/*.md 2>/dev/null

For each thread, read the first few lines to show title and status:

## Active Threads

| Thread | Status | Last Updated |
|--------|--------|-------------|
| fix-deploy-key-auth | OPEN | 2026-03-15 |
| pasta-tcp-timeout | RESOLVED | 2026-03-12 |
| perf-investigation | IN PROGRESS | 2026-03-17 |

If no threads exist, show:

No threads found. Create one with: /gsd:thread <description>

</mode_list>

<mode_resume> If {{arguments}} matches an existing thread name (file exists):

Resume the thread — load its context into the current session:

cat ".planning/threads/{{THREAD_NAME}}.md"

Display the thread content and ask what the user wants to work on next. Update the thread's status to IN PROGRESS if it was OPEN. </mode_resume>

<mode_create> If {{arguments}} is a new description (no matching thread file):

Create a new thread:

Generate slug from description:

SLUG=$(node "/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs" generate-slug "{{arguments}}")

Create the threads directory if needed:
```
mkdir -p .planning/threads
```

Write the thread file:

cat > ".planning/threads/{{SLUG}}.md" << 'EOF'
# Thread: {description}

## Status: OPEN

## Goal

{description}

## Context

*Created from conversation on {today's date}.*

## References

- *(add links, file paths, or issue numbers)*

## Next Steps

- *(what the next session should do first)*
EOF

If there's relevant context in the current conversation (code snippets, error messages, investigation results), extract and add it to the Context section.

Commit:

node "/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs" commit "docs: create thread — {{ARGUMENTS}}" --files ".planning/threads/{{SLUG}}.md"

Report:

## 🧵 Thread Created

Thread: {slug}
File: .planning/threads/{slug}.md

Resume anytime with: /gsd:thread {slug}

</mode_create>

Install gsd:thread 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> Create, list, or resume persistent context threads. Threads are lightweight cross-session knowledge stores for work that spans multiple sessions but doesn't belong to any specific phase. </objective> <process> **Parse {{arguments}} to determine mode:** <mode_list> **If no arguments or {{arguments}} is empty:** List all threads: ```bash ls .planning/threads/*.md 2>/dev/null ``` For each thread, read the first few lines to show title and status: ``` ## Active Threads | Thread | Status | Last Updated | |--------|--------|-------------| | fix-deploy-key-auth | OPEN | 2026-03-15 | | pasta-tcp-timeout | RESOLVED | 2026-03-12 | | perf-investigation | IN PROGRESS | 2026-03-17 | ``` If no threads exist, show: ``` No threads found. Create one with: /gsd:thread <description> ``` </mode_list> <mode_resume> **If {{arguments}} matches an existing thread name (file exists):** Resume the thread — load its context into the current session: ```bash cat ".planning/threads/{{THREAD_NAME}}.md" ``` Display the thread content and ask what the user wants to work on next. Update the thread's status to `IN PROGRESS` if it was `OPEN`. </mode_resume> <mode_create> **If {{arguments}} is a new description (no matching thread file):** Create a new thread: 1. Generate slug from description: ```bash SLUG=$(node "/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs" generate-slug "{{arguments}}") ``` 2. Create the threads directory if needed: ```bash mkdir -p .planning/threads ``` 3. Write the thread file: ```bash cat > ".planning/threads/{{SLUG}}.md" << 'EOF' # Thread: {description} ## Status: OPEN ## Goal {description} ## Context *Created from conversation on {today's date}.* ## References - *(add links, file paths, or issue numbers)* ## Next Steps - *(what the next session should do first)* EOF ``` 4. If there's relevant context in the current conversation (code snippets, error messages, investigation results), extract and add it to the Context section. 5. Commit: ```bash node "/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs" commit "docs: create thread — {{ARGUMENTS}}" --files ".planning/threads/{{SLUG}}.md" ``` 6. Report: ``` ## 🧵 Thread Created Thread: {slug} File: .planning/threads/{slug}.md Resume anytime with: /gsd:thread {slug} ``` </mode_create> </process> <notes> - Threads are NOT phase-scoped — they exist independently of the roadmap - Lighter weight than /gsd:pause-work — no phase state, no plan context - The value is in Context and Next Steps — a cold-start session can pick up immediately - Threads can be promoted to phases or backlog items when they mature: /gsd:add-phase or /gsd:add-backlog with context from the thread - Thread files live in .planning/threads/ — no collision with phases or other GSD structures </notes>

{ "prompt": "<objective>\nCreate, list, or resume persistent context threads. Threads are lightweight\ncross-session knowledge stores for work that spans multiple sessions but\ndoesn't belong to any specific phase.\n</objective>\n\n<process>\n\n**Parse {{arguments}} to determine mode:**\n\n<mode_list>\n**If no arguments or {{arguments}} is empty:**\n\nList all threads:\n```bash\nls .planning/threads/*.md 2>/dev/null\n```\n\nFor each thread, read the first few lines to show title and status:\n```\n## Active Threads\n\n| Thread | Status | Last Updated |\n|--------|--------|-------------|\n| fix-deploy-key-auth | OPEN | 2026-03-15 |\n| pasta-tcp-timeout | RESOLVED | 2026-03-12 |\n| perf-investigation | IN PROGRESS | 2026-03-17 |\n```\n\nIf no threads exist, show:\n```\nNo threads found. Create one with: /gsd:thread <description>\n```\n</mode_list>\n\n<mode_resume>\n**If {{arguments}} matches an existing thread name (file exists):**\n\nResume the thread — load its context into the current session:\n```bash\ncat \".planning/threads/{{THREAD_NAME}}.md\"\n```\n\nDisplay the thread content and ask what the user wants to work on next.\nUpdate the thread's status to `IN PROGRESS` if it was `OPEN`.\n</mode_resume>\n\n<mode_create>\n**If {{arguments}} is a new description (no matching thread file):**\n\nCreate a new thread:\n\n1. Generate slug from description:\n ```bash\n SLUG=$(node \"/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs\" generate-slug \"{{arguments}}\")\n ```\n\n2. Create the threads directory if needed:\n ```bash\n mkdir -p .planning/threads\n ```\n\n3. Write the thread file:\n ```bash\n cat > \".planning/threads/{{SLUG}}.md\" << 'EOF'\n # Thread: {description}\n\n ## Status: OPEN\n\n ## Goal\n\n {description}\n\n ## Context\n\n *Created from conversation on {today's date}.*\n\n ## References\n\n - *(add links, file paths, or issue numbers)*\n\n ## Next Steps\n\n - *(what the next session should do first)*\n EOF\n ```\n\n4. If there's relevant context in the current conversation (code snippets,\n error messages, investigation results), extract and add it to the Context\n section.\n\n5. Commit:\n ```bash\n node \"/Users/anish/Developer/Personal/LibM/.claude/get-shit-done/bin/gsd-tools.cjs\" commit \"docs: create thread — {{ARGUMENTS}}\" --files \".planning/threads/{{SLUG}}.md\"\n ```\n\n6. Report:\n ```\n ## 🧵 Thread Created\n\n Thread: {slug}\n File: .planning/threads/{slug}.md\n\n Resume anytime with: /gsd:thread {slug}\n ```\n</mode_create>\n\n</process>\n\n<notes>\n- Threads are NOT phase-scoped — they exist independently of the roadmap\n- Lighter weight than /gsd:pause-work — no phase state, no plan context\n- The value is in Context and Next Steps — a cold-start session can pick up immediately\n- Threads can be promoted to phases or backlog items when they mature:\n /gsd:add-phase or /gsd:add-backlog with context from the thread\n- Thread files live in .planning/threads/ — no collision with phases or other GSD structures\n</notes>", "variables": [ "arguments", "THREAD_NAME", "SLUG", "ARGUMENTS" ], "notes": "Manage persistent context threads for cross-session work Tools: Read, Write, Bash. Arguments: [name | description].", "metadata": { "source": { "provider": "github-claude-commands", "repository": "https://github.com/AnishMulay/LibM", "path": ".claude/commands/gsd/thread.md", "ref": "266dd23e42713636e99e9511ec4c0fe2fc68dd67", "url": "https://github.com/AnishMulay/LibM/blob/266dd23e42713636e99e9511ec4c0fe2fc68dd67/.claude/commands/gsd/thread.md", "key": "AnishMulay/LibM/.claude/commands/gsd/thread.md" } } }

gsd:thread

About

Install gsd:thread 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