Roadmap: agent coverage strategy beyond v0.1

## Context

abtop v0.1 was intentionally scoped to Claude Code + Codex CLI, with Gemini/Cursor listed as **Non-Goals** in `CLAUDE.md`. Since then, the project has grown and several contributors have opened PRs adding support for additional agents:

- ✅ **OpenCode** — merged via #40 and released in `v0.4.3`
- 🟡 **Gemini CLI** — #41 (currently Draft, pending this decision)
- 🟡 **Kiro CLI** — #44 (currently Draft, pending this decision)
- 🟡 **Pi** — #63 (candidate for this same policy decision)

Evaluating each new agent ad-hoc isn't fair to contributors (they invest significant work before knowing whether it'll land) and isn't good for the project's long-term shape. Time to define a strategy.

## Current status (2026-05-09)

OpenCode is no longer pending. It is now in core, documented in the README, and available in `v0.4.3`.

OpenCode's supported surface is intentionally narrower than Claude/Codex for now:

- Session discovery from `~/.local/share/opencode/opencode.db`
- Token tracking from local DB totals
- Status detection
- Git status
- Children / ports

Quota/rate-limit gauges remain Claude + Codex only because OpenCode does not expose matching account-level quota data in the same way.

## Questions to answer

1. **What's the inclusion bar?** Criteria could include:
- User base / popularity
- Stability of the underlying data source (the agent's session files, DB, or API)
- Maintenance cost — how often does the agent change its format?
- Whether abtop's UI abstractions (context %, tokens, rate limits) meaningfully apply

2. **Should core support more agents, or should there be a plugin mechanism?**
- Pros of in-tree: consistent UX, single binary, easy install
- Pros of plugins: independent release cadence, lower core maintenance, community can add niche agents without approval
- A plugin path via the existing `AgentCollector` trait may be feasible

3. **What happens to the `Non-Goals (v0.1)` list in `CLAUDE.md`?**
- Update it to reflect whatever is decided
- Decide whether abtop is moving to a broader scope, or staying focused

4. **Release implications** — each new agent is a new data source to keep working across CLI version changes. Need a realistic estimate of the maintenance tail.

## Proposed next step

Keep this issue open for the broader agent coverage policy. OpenCode itself is done, but the general decision still needs to be made before merging additional agent collectors.

- [x] Ship OpenCode in core (#40, `v0.4.3`)
- [ ] Decide which additional agents to include in core
- [ ] Decide whether to add feature flags, an external collector protocol, or both
- [ ] Evaluate pending agent PRs (#41, #44, #63) against the criteria
- [ ] Update `CLAUDE.md` Non-Goals accordingly
- [ ] Communicate the outcome on the pending PRs

## Related

- #40 (merged, OpenCode)
- #41 (draft, Gemini)
- #44 (draft, Kiro)
- #63 (Pi)