runner-research
Runner Research
Research AI agent runners to keep LeanSpec's runner registry and configurations current as the ecosystem evolves rapidly.
Workflow
1. Gather Current State
Read the runner registry source to understand what LeanSpec currently supports:
rust/leanspec-core/src/sessions/runner.rs # RunnerRegistry::builtins()
Read the current runner catalog reference for known details:
- See references/runners-catalog.md for the full catalog of tracked runners
2. Research Updates
For each runner category, use web_search to check for:
- Config format changes — New or renamed config files/dirs (e.g.,
.cursorrules→.cursor/rules) - CLI changes — New commands, renamed binaries, new flags
- New environment variables — API key changes, new auth mechanisms
- New capabilities — MCP support, tool use, context protocol changes
- Deprecations — Removed features, sunset announcements
- New runners — Emerging agent platforms not yet tracked
Prioritize runners by adoption and rate of change:
- Tier 1 (high priority): Claude Code, Copilot, Cursor, Windsurf, Codex, Gemini
- Tier 2 (medium): Kiro, Amp, Aider, Goose, Continue, Roo Code
- Tier 3 (monitor): Droid, Kimi, Qodo, Trae, Qwen Code, OpenHands, Crush, CodeBuddy, Kilo, Augment
3. Compare & Identify Gaps
Cross-reference findings against the registry:
- Missing detection commands or config dirs
- Outdated env var names
- New runners worth adding
- Runners that have been discontinued
4. Report Findings
Produce output based on significance:
- Minor updates (typos, env var additions): Update
references/runners-catalog.mddirectly - Major changes (new config formats, new runners, breaking changes): Create a new spec via the leanspec-sdd skill describing what needs to change in the runner registry
5. Update the Catalog
After research, update references/runners-catalog.md with:
- New findings, dates checked, version numbers
- Any corrections to detection config
- New runners discovered
Key Source Files
| File | Purpose |
|---|---|
rust/leanspec-core/src/sessions/runner.rs |
Runner registry with detection config |
schemas/runners.json |
JSON schema for custom runner config |
packages/cli/templates/_shared/agents-components/ |
AGENTS.md template components |
packages/cli/templates/*/AGENTS.md |
Generated AGENTS.md templates |
Research Sources
Use web_search with queries like:
"{runner-name} CLI changelog 2025 2026""{runner-name} agent config file format""{runner-name} MCP support""new AI coding agent CLI 2026""site:github.com {runner-org}/{runner-repo} releases"
More from codervisor/lean-spec
agent-browser
Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.
49leanspec-development
Development workflows, commands, publishing, CI/CD, changelog management, and contribution guidelines for LeanSpec. Use when contributing code, fixing bugs, setting up dev environment, running tests or linting, working with the monorepo structure, looking up build/dev/test/publish/format/lint commands, preparing releases, publishing to npm, bumping versions, syncing package versions, testing dev builds, troubleshooting npm distribution, updating changelogs, triggering CI/CD workflows, monitoring build status, debugging failed runs, managing artifacts, checking CI before releases, or researching AI agent runners. Triggers include any development, scripting, publishing, CI/CD, changelog, or runner research task in this project.
39parallel-worktrees
>
35leanspec-sdd
Spec-Driven Development methodology for AI-assisted development. Use when working with specs, planning features, creating/implementing/refining/organizing specs, checking progress, updating specs, task breakdowns, design decisions, or any task involving a specs/ folder or .lean-spec/config.json.
16github-actions
GitHub Actions workflow management for LeanSpec. Use when triggering CI/CD workflows, monitoring build status, debugging failed runs, managing artifacts, or checking CI before releases.
3leanspec-scripts
All pnpm and cargo commands for LeanSpec development. Use when looking up build, dev, test, publish, format, lint, or validation commands.
3