// Run and maintain Con's terminal-agent benchmark against a live app session. Use when validating con-cli, SSH workspace reuse, tmux awareness, agent-target preparation, or when collecting benchmark evidence for regressions and release notes.
Validate Con's local socket control plane against a real running app session, and write/run con-test integration tests. Use when testing con-cli, the Unix socket API, pane control, tmux control, in-session agent calls, or when writing E2E test cases in crates/con-test/testdata/.
Maintain Con's CHANGELOG.md and release notes. Use when updating changelog entries, preparing a beta/dev release, reviewing PR release-note coverage, or ensuring contributor PR credit is present.
Run a benchmark-driven improvement loop for Con's terminal agent. Use when iterating on pane awareness, SSH/tmux behavior, coding-cli flows, benchmark scoring, or progress tracking across many runs.
| name | terminal-agent-benchmark |
| description | Run and maintain Con's terminal-agent benchmark against a live app session. Use when validating con-cli, SSH workspace reuse, tmux awareness, agent-target preparation, or when collecting benchmark evidence for regressions and release notes. |
Use this skill when you need to evaluate Con as a terminal-native agent, not just compile it.
Primary references:
python3 benchmarks/terminal-agent/run.py --suite strictCON_BENCH_ENABLE_AGENT=1 python3 benchmarks/terminal-agent/run.py --suite allpython3 benchmarks/terminal-agent/run.py --list-profilespython3 benchmarks/terminal-agent/run.py --profile basic-local-shellCON_BENCH_ENABLE_AGENT=1 python3 benchmarks/terminal-agent/run.py --profile basic-local-codex --suite allpython3 benchmarks/terminal-agent/run.py --profile operator-local-codex-devloop --suite operatorpython3 benchmarks/terminal-agent/run.py --profile operator-local-claude-devloop --suite operatorpython3 benchmarks/terminal-agent/run.py --profile operator-local-opencode-devloop --suite operatorpython3 benchmarks/terminal-agent/run.py --profile operator-ssh-dual-host-maintenance --suite operatorpython3 benchmarks/terminal-agent/run.py --profile operator-ssh-tmux-devloop --suite operatorbenchmarks/terminal-agent/playbooks/..context/benchmarks/ and cite it in your report.python3 benchmarks/terminal-agent/score.py --profile ... --record ... --score ...python3 benchmarks/terminal-agent/report.pypane_id over pane_index when following up on benchmark findings.panes.* API unless the benchmark
explicitly targets pane-local surfaces. Surface support is additive and should
not change the built-in agent's pane/tool contract.agent ask turns. If a tab already has a pending agent request, let the runner wait and reuse the same tab instead of opening a parallel benchmark against it.