npx agentspec-cli install 407b01fb-bf60-44b3-894d-9d4c7e1ab233 --file-type agents-md→ .agents/
# Case — Agent Harness
Spine repo for orchestrating agent work across WorkOS open source projects.
Humans steer. Agents execute. When agents struggle, fix the harness.
## First Step
Run the session command to gather context before doing anything else:
```bash
SESSION=$(ca session <target-repo-path> --task <task.json>)
echo "$SESSION"
```
## Projects
| Repo | Path | Purpose | Stack |
| ---------------------- | --------------------------- | ---------------------------------------------------- | ------- |
| cli | `../cli/main` | WorkOS CLI — AuthKit installers, resource management | TS/pnpm |
| skills | `../skills` | WorkOS integration skills | TS/pnpm |
| authkit-session | `../authkit-session` | Framework-agnostic session management | TS/pnpm |
| authkit-tanstack-start | `../authkit-tanstack-start` | AuthKit TanStack Start SDK | TS/pnpm |
| authkit-nextjs | `../authkit-nextjs` | AuthKit Next.js SDK | TS/pnpm |
| workos-node | `../workos-node/main` | WorkOS Node.js SDK | TS/npm |
Full metadata (commands, remotes, evidence strategy): `~/.config/case/projects.json`
## Navigation
| Topic | Location |
| --------------------- | ---------------------------------------- |
| Architecture patterns | `docs/architecture/` |
| Shared conventions | `docs/conventions/` |
| Golden principles | `docs/golden-principles.md` |
| Failure matrix | `docs/failure-matrix.md` |
| Playbooks | `docs/playbooks/` |
| Agent roles | `agents/` |
| Entropy management | `docs/conventions/entropy-management.md` |
| Repo learnings | Target repo `.case/learnings.md` |
## Task Dispatch
Tasks are markdown files that agents execute. Runtime task files live in the target repo's ignored `.case/tasks/active/`.
- **Format spec**: `tasks/README.md`
- **Templates**: `tasks/templates/`
Pipeline: scout → implementer → verifier → reviewer → closer → (retrospective)
Onboarding agent (out of the pipeline): `interviewer` — invoked by `ca onboard --interview` to capture evidence strategy rationale, verification notes, and repo learnings.
Lifecycle: `.case/tasks/active/` → PR opened/merged status in the task JSON
## Working in a Target Repo
0. Run `ca session {repo-path} --task {task-json}` to gather context
1. Read the repo's `CLAUDE.md` (or `CLAUDE.local.md`) for project-specific instructions
2. Run `ca bootstrap {repo-name}` to verify readiness
3. Follow the repo's PR checklist before opening a PR
4. Run `ca check --repo {repo-name}` to verify conventions
## Maintenance
- **Convention checks**: `ca check` — enforce shared rules
## Improving This Harness
See `CLAUDE.md` for how to maintain and improve case itself.
Bootstrap Agent Instructions
You are a harness engineering agent. Your job is to make a target repository AI-native by generating tailored harness artifacts — `CLAUDE.md`, `AGENTS.md`, `ARCHITECTURE.md`, CI integration, and related configuration files. You operate from this bootstrap repo and write outputs into the target repo.
by AgentHub Crawler
AI Harness — Agent Instructions
You are a self-improving personal AI agent for Anderson Edmond. You operate across Discord and iMessage, run background tasks on schedule, and continuously learn from every interaction.
by AgentHub Crawler
VirtEngine AGENTS System — Repo Guide
Always work on tasks longer than you think are needed to accomodate edge case scenarios, testing, ensuring it works, implementing connecting logic and ensuring high quality of standards. NEVER START A PLAN AND THEN ASK FOR USER INPUT, OR ASK FOR USER INPUT DURING A COMPLETION OF A TASK - ONCE YOU ARE ASSIGNED A PROPER TASK - YOU MUST COMPLETE IT END TO END. IF YOU ARE ASSIGNED A TASK OF AN ALREADY COMPLETED TASK THAT YOU ARE ANALYZING TO ENSURE COMPLETENESS, IF YOU DO FIND GAPS DON'T ASK FOR CON
Sign in to leave a comment.
by AgentHub Crawler