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.

personal-runbooks-portfolio - Skill

Name: personal-runbooks-portfolio
Author: lapc506

Imported from lapc506/personal-runbooks-portfolio (AGENTS.md). Install upstream with npx skills add lapc506/personal-runbooks-portfolio. Copyright stays with the author.

AGENTS.md

This repository follows the PRDS standard from chimeranext/better-toolkits and requires PRs to be reviewable, scoped, and human-approved. GitHub Issues are the sole tracker of record: use real issue numbers and Fixes #N; do not invent Linear-style TICKET-* identifiers. The upstream /toolkits-initial-setup bootstrap command is the single source of truth for harness setup and local tooling wiring; do not drift into a repo-local fork of that protocol.

Required PR behavior

Use a conventional-commit style title for every PR subject:
- feat(scope): add capability
- fix(scope): resolve regression
- docs(pr): align repo to PRDS (#14)
- chore(ci): update templates
Branch names must follow the pattern type/<issue-number>-slug with a lowercase numeric GitHub issue number (for example, feat/13-ai-risk-cards).
Every PR must include the PRDS sections in the body:
- Summary
- Tracker
- Test plan
- Scope boundaries
- Risk / rollout
- Screenshots / evidence
The PR description is part of the deliverable and must be written before the PR is marked ready for review.
Keep each PR focused; do not bundle unrelated refactors or broad cleanup into the same change.
Draft PRs are the default until a human explicitly approves the review.

Required title format

<type>(<scope>): <outcome> (#N)

Examples:

docs(pr): use GitHub-native issue tracking (#14)
feat(winui): add AI risk cards (#13)

Required PR body template

## Summary

- What changed
- Why now
- How it was implemented

## Tracker

Fixes #N

- Issue: https://github.com/lapc506/personal-runbooks-portfolio/issues/N
- OpenSpec: `N/A` or path
- Cross-repo siblings (if any): link other PR URLs here

## Test plan

- [ ] <concrete verification command>
- [ ] <validation result>

## Scope boundaries

- Out of scope:
- No unrelated refactors

## Risk / rollout

- Risk: low / medium / high
- Rollout: `N/A` or specific steps

## Screenshots / evidence

- UI: `N/A` or screenshots
- Logs: `N/A` or link

Enforcement

The repository owners expect all future PRs to follow this policy from this point onward.

Install personal-runbooks-portfolio 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.

{ "ocm": "1", "id": "lapc506-personal-runbooks-portfolio-personal-runbooks-portfolio", "kind": "skill", "name": "personal-runbooks-portfolio", "description": "This repository follows the PRDS standard from chimeranext/better-toolkits and requires PRs to be reviewable, scoped, and human-approved. GitHub Issues are the sole tracker of record: use real issue numbers and `Fixes #N`; do not invent Linear-style `TICKET-*` identifiers. The upstream `/toolkits-initial-setup` bootstrap command is the single source of truth for harness setup and local tooling wiring; do not drift into a repo-local fork of that protocol.", "publisher": "lapc506", "version": "1.0.0", "capabilities": { "domains": [ "finance", "customer_support" ], "tags": [ "skill-md", "github-agents" ], "languages": [ "en" ] }, "quality_prior": 0.6, "examples": [ "This repository follows the PRDS standard from chimeranext/better-toolkits and requires PRs to be reviewable, scoped, and human-approved. GitHub Issues are the sole tracker of record: use real issue numbers and `Fixes #N`; do not invent Linear-style `TICKET-*` identifiers. The upstream `/toolkits-initial-setup` bootstrap command is the single source of truth for harness setup and local tooling wiring; do not drift into a repo-local fork of that protocol." ], "primary": false, "metadata": { "source": { "provider": "github-agents", "repository": "https://github.com/lapc506/personal-runbooks-portfolio", "path": "AGENTS.md", "ref": "b6f89d07452e76c8190a122cc8e0aa723152e2ad", "url": "https://github.com/lapc506/personal-runbooks-portfolio/blob/b6f89d07452e76c8190a122cc8e0aa723152e2ad/AGENTS.md", "key": "lapc506/personal-runbooks-portfolio/AGENTS.md" } }, "instructions": "# AGENTS.md\n\nThis repository follows the PRDS standard from chimeranext/better-toolkits and requires PRs to be reviewable, scoped, and human-approved. GitHub Issues are the sole tracker of record: use real issue numbers and `Fixes #N`; do not invent Linear-style `TICKET-*` identifiers. The upstream `/toolkits-initial-setup` bootstrap command is the single source of truth for harness setup and local tooling wiring; do not drift into a repo-local fork of that protocol.\n\n## Required PR behavior\n\n- Use a conventional-commit style title for every PR subject:\n - `feat(scope): add capability`\n - `f", "cost": { "context_tokens": 538 } }

personal-runbooks-portfolio

About

AGENTS.md

Required PR behavior

Required title format

Required PR body template

Enforcement

Install personal-runbooks-portfolio 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