@jstn-sdk/rcs 0.1.0 → 0.1.6

package/skills/ralplan/SKILL.md

@@ -1,162 +0,0 @@
----
-name: ralplan
-description: Alias for $plan --consensus
----
-
-# Ralplan (Consensus Planning Alias)
-
-Ralplan is a shorthand alias for `$plan --consensus`. It triggers iterative planning with Planner, Architect, and Critic agents until consensus is reached, with **RALPLAN-DR structured deliberation** (short mode by default, deliberate mode for high-risk work).
-
-## Usage
-
-```
-$ralplan "task description"
-```
-
-## Flags
-
-- `--interactive`: Enables user prompts at key decision points (draft review in step 2 and final approval in step 6). Without this flag the workflow runs fully automated — Planner → Architect → Critic loop — and outputs the final plan without asking for confirmation.
-- `--deliberate`: Forces deliberate mode for high-risk work. Adds pre-mortem (3 scenarios) and expanded test planning (unit/integration/e2e/observability). Without this flag, deliberate mode can still auto-enable when the request explicitly signals high risk (auth/security, migrations, destructive changes, production incidents, compliance/PII, public API breakage).
-
-## Usage with interactive mode
-
-```
-$ralplan --interactive "task description"
-```
-
-## Behavior
-
-## GPT-5.5 Guidance Alignment
-
-Use the shared workflow guidance pattern: outcome-first framing, concise visible updates for multi-step planning, local overrides for the active workflow branch, evidence-backed planning and validation expectations, explicit stop rules, right-sized implementation/PRD shape, and automatic continuation for safe reversible steps. Ask only for material, destructive, credentialed, external-production, or preference-dependent branches.
-
-This skill invokes the Plan skill in consensus mode:
-
-```
-$plan --consensus <arguments>
-$plan --consensus --interactive <arguments>
-```
-
-The consensus workflow:
-1. **Planner** creates an adaptive plan (right-sized to task scope; do not default to exactly five steps) and a compact **RALPLAN-DR summary** before review:
-   - Principles (3-5)
-   - Decision Drivers (top 3)
-   - Viable Options (>=2) with bounded pros/cons
-   - If only one viable option remains, explicit invalidation rationale for alternatives
-   - Deliberate mode only: pre-mortem (3 scenarios) + expanded test plan (unit/integration/e2e/observability)
-2. **User feedback** *(--interactive only)*: If `--interactive` is set, use the structured question UI (`rcs question` in attached tmux; native structured input outside tmux when available) to present the draft plan **plus the Principles / Drivers / Options summary** before review (Proceed to review / Request changes / Skip review). Otherwise, automatically proceed to review.
-3. **Architect** reviews for architectural soundness and must provide the strongest steelman antithesis, at least one real tradeoff tension, and (when possible) synthesis — **await completion before step 4**. In deliberate mode, Architect should explicitly flag principle violations.
-4. **Critic** evaluates against quality criteria — run only after step 3 completes. Critic must enforce principle-option consistency, fair alternatives, risk mitigation clarity, testable acceptance criteria, and concrete verification steps. In deliberate mode, Critic must reject missing/weak pre-mortem or expanded test plan.
-5. **Re-review loop** (max 5 iterations): Any non-`APPROVE` Critic verdict (`ITERATE` or `REJECT`) MUST run the same full closed loop:
-   a. Collect Architect + Critic feedback
-   b. Revise the plan with Planner
-   c. Return to Architect review
-   d. Return to Critic evaluation
-   e. Repeat this loop until Critic returns `APPROVE` or 5 iterations are reached
-   f. If 5 iterations are reached without `APPROVE`, present the best version to the user
-6. On Critic approval *(--interactive only)*: If `--interactive` is set, use the structured question UI to present the plan with approval options (Approve and execute via ralph / Approve and implement via team / Request changes / Reject). Final plan must include ADR (Decision, Drivers, Alternatives considered, Why chosen, Consequences, Follow-ups), an explicit available-agent-types roster, concrete follow-up staffing guidance for both `ralph` and `team`, suggested reasoning levels by lane, explicit `rcs team` / `$team` launch hints, and a concrete **team verification** path. Otherwise, output the final plan and stop.
-7. *(--interactive only)* User chooses: Approve (ralph or team), Request changes, or Reject
-8. *(--interactive only)* On approval: invoke `$ralph` for sequential execution or `$team` for parallel team execution with the explicit available-agent-types roster, reasoning-by-lane guidance, role/staffing allocation guidance, launch hints, and verification-path guidance from the approved plan -- never implement directly
-
-> **Important:** Steps 3 and 4 MUST run sequentially. Do NOT issue both agent calls in the same parallel batch. Always await the Architect result before invoking Critic.
-
-Follow the Plan skill's full documentation for consensus mode details.
-
-## Pre-context Intake
-
-Before consensus planning or execution handoff, ensure a grounded context snapshot exists:
-
-1. Derive a task slug from the request.
-2. Reuse the latest relevant snapshot in `.rcs/context/{slug}-*.md` when available.
-3. If none exists, create `.rcs/context/{slug}-{timestamp}.md` (UTC `YYYYMMDDTHHMMSSZ`) with:
-   - task statement
-   - desired outcome
-   - known facts/evidence
-   - constraints
-   - unknowns/open questions
-   - likely codebase touchpoints
-4. If ambiguity remains high, gather brownfield facts first. When session guidance enables `USE_RCS_EXPLORE_CMD`, prefer `rcs explore` for simple read-only repository lookups with narrow, concrete prompts; otherwise use the richer normal explore path. Then run `$deep-interview --quick <task>` before continuing.
-5. If the plan depends on official docs, version-aware framework guidance, best practices, or external dependency behavior, auto-delegate `researcher` before finalizing the planning handoff so execution does not start from repo-local recall alone.
-
-Do not hand off to execution modes until this intake is complete; if urgency forces progress, explicitly document the risk tradeoffs.
-
-## Pre-Execution Gate
-
-### Why the Gate Exists
-
-Execution modes (ralph, autopilot, team, ultrawork) spin up heavy multi-agent orchestration. When launched on a vague request like "ralph improve the app", agents have no clear target — they waste cycles on scope discovery that should happen during planning, often delivering partial or misaligned work that requires rework.
-
-The ralplan-first gate intercepts underspecified execution requests and redirects them through the ralplan consensus planning workflow. This ensures:
-- **Explicit scope**: A PRD defines exactly what will be built
-- **Test specification**: Acceptance criteria are testable before code is written
-- **Consensus**: Planner, Architect, and Critic agree on the approach
-- **No wasted execution**: Agents start with a clear, bounded task
-
-### Good vs Bad Prompts
-
-**Passes the gate** (specific enough for direct execution):
-- `ralph fix the null check in src/hooks/bridge.ts:326`
-- `autopilot implement issue #42`
-- `team add validation to function processKeywordDetector`
-- `ralph do:\n1. Add input validation\n2. Write tests\n3. Update README`
-- `ultrawork add the user model in src/models/user.ts`
-
-**Gated — redirected to ralplan** (needs scoping first):
-- `ralph fix this`
-- `autopilot build the app`
-- `team improve performance`
-- `ralph add authentication`
-- `ultrawork make it better`
-
-**Bypass the gate** (when you know what you want):
-- `force: ralph refactor the auth module`
-- `! autopilot optimize everything`
-
-### When the Gate Does NOT Trigger
-
-The gate auto-passes when it detects **any** concrete signal. You do not need all of them — one is enough:
-
-| Signal Type | Example prompt | Why it passes |
-|---|---|---|
-| File path | `ralph fix src/hooks/bridge.ts` | References a specific file |
-| Issue/PR number | `ralph implement #42` | Has a concrete work item |
-| camelCase symbol | `ralph fix processKeywordDetector` | Names a specific function |
-| PascalCase symbol | `ralph update UserModel` | Names a specific class |
-| snake_case symbol | `team fix user_model` | Names a specific identifier |
-| Test runner | `ralph npm test && fix failures` | Has an explicit test target |
-| Numbered steps | `ralph do:\n1. Add X\n2. Test Y` | Structured deliverables |
-| Acceptance criteria | `ralph add login - acceptance criteria: ...` | Explicit success definition |
-| Error reference | `ralph fix TypeError in auth` | Specific error to address |
-| Code block | `ralph add: \`\`\`ts ... \`\`\`` | Concrete code provided |
-| Escape prefix | `force: ralph do it` or `! ralph do it` | Explicit user override |
-
-### End-to-End Flow Example
-
-1. User types: `ralph add user authentication`
-2. Gate detects: execution keyword (`ralph`) + underspecified prompt (no files, functions, or test spec)
-3. Gate redirects to **ralplan** with message explaining the redirect
-4. Ralplan consensus runs:
-   - **Planner** creates initial plan (which files, what auth method, what tests)
-   - **Architect** reviews for soundness
-   - **Critic** validates quality and testability
-5. On consensus approval, user chooses execution path:
-   - **ralph**: sequential execution with verification
-   - **team**: parallel coordinated agents
-6. Execution begins with a clear, bounded plan
-
-### Troubleshooting
-
-| Issue | Solution |
-|-------|----------|
-| Gate fires on a well-specified prompt | Add a file reference, function name, or issue number to anchor the request |
-| Want to bypass the gate | Prefix with `force:` or `!` (e.g., `force: ralph fix it`) |
-| Gate does not fire on a vague prompt | The gate only catches prompts with <=15 effective words and no concrete anchors; add more detail or use `$ralplan` explicitly |
-| Redirected to ralplan but want to skip planning | In the ralplan workflow, say "just do it" or "skip planning" to transition directly to execution |
-
-## Scenario Examples
-
-**Good:** The user says `continue` after the workflow already has a clear next step. Continue the current branch of work instead of restarting or re-asking the same question.
-
-**Good:** The user changes only the output shape or downstream delivery step (for example `make a PR`). Preserve earlier non-conflicting workflow constraints and apply the update locally.
-
-**Bad:** The user says `continue`, and the workflow restarts discovery or stops before the missing verification/evidence is gathered.

package/src/scripts/eval/eval-adaptive-sort-optimization.py

@@ -1,24 +0,0 @@
-from __future__ import annotations
-
-import json
-import subprocess
-import sys
-
-result = subprocess.run(
-    [sys.executable, 'playground/adaptive_sort_demo/sort_benchmark.py'],
-    check=False,
-    capture_output=True,
-    text=True,
-)
-if result.stdout:
-    sys.stderr.write(result.stdout)
-if result.stderr:
-    sys.stderr.write(result.stderr)
-if result.returncode != 0:
-    print(json.dumps({'pass': False, 'score': 0.0}))
-    raise SystemExit(result.returncode)
-
-payload = json.loads(result.stdout)
-total_cost = float(payload['total_cost'])
-score = 10000.0 / total_cost
-print(json.dumps({'pass': total_cost > 0, 'score': score}))

package/src/scripts/eval/eval-candidate-handoff.ts

@@ -1,8 +0,0 @@
-import { spawnSync } from 'node:child_process';
-const result = spawnSync('node', ['--test', 'dist/autoresearch/__tests__/runtime.test.js', 'dist/autoresearch/__tests__/contracts.test.js'], {
-  encoding: 'utf-8',
-});
-process.stdout.write(JSON.stringify({ pass: result.status === 0 }));
-if (result.stdout) process.stderr.write(result.stdout);
-if (result.stderr) process.stderr.write(result.stderr);
-process.exit(result.status ?? 1);

package/src/scripts/eval/eval-cli-discoverability.ts

@@ -1,40 +0,0 @@
-#!/usr/bin/env node
-import { spawnSync } from 'node:child_process';
-
-const checks: [string, string[]][] = [
-  ['node', ['--test', 'dist/cli/__tests__/index.test.js']],
-  ['node', ['--test', 'dist/cli/__tests__/nested-help-routing.test.js']],
-  ['node', ['--test', 'dist/cli/__tests__/sparkshell-cli.test.js']],
-  ['node', ['--test', 'dist/cli/__tests__/session-search-help.test.js']],
-];
-
-function run(command: string, args: string[]) {
-  const result = spawnSync(command, args, {
-    encoding: 'utf-8',
-    stdio: ['ignore', 'pipe', 'pipe'],
-  });
-  return {
-    command: [command, ...args].join(' '),
-    status: result.status ?? 1,
-    stdout: (result.stdout || '').trim(),
-    stderr: (result.stderr || '').trim(),
-  };
-}
-
-const build = run('npm', ['run', 'build']);
-const results = [build, ...checks.map(([command, args]) => run(command, args))];
-const passed = results.filter((result) => result.status === 0).length;
-const score = Number((passed / results.length).toFixed(2));
-const pass = results.every((result) => result.status === 0);
-
-console.log(JSON.stringify({
-  pass,
-  score,
-  summary: 'CLI discoverability pilot evaluator',
-  details: results.map(({ command, status, stderr }) => ({
-    command,
-    ok: status === 0,
-    status,
-    stderr: stderr || undefined,
-  })),
-}));

package/src/scripts/eval/eval-fresh-run-tagging.ts

@@ -1,8 +0,0 @@
-import { spawnSync } from 'node:child_process';
-const result = spawnSync('node', ['--test', 'dist/team/__tests__/worktree.test.js', 'dist/cli/__tests__/autoresearch.test.js'], {
-  encoding: 'utf-8',
-});
-process.stdout.write(JSON.stringify({ pass: result.status === 0 }));
-if (result.stdout) process.stderr.write(result.stdout);
-if (result.stderr) process.stderr.write(result.stderr);
-process.exit(result.status ?? 1);

package/src/scripts/eval/eval-help-consistency.ts

@@ -1,11 +0,0 @@
-import { spawnSync } from 'node:child_process';
-
-const result = spawnSync('node', ['--test', 'dist/cli/__tests__/session-search-help.test.js'], {
-  encoding: 'utf-8',
-});
-
-const pass = result.status === 0;
-process.stdout.write(JSON.stringify({ pass }));
-if (result.stdout) process.stderr.write(result.stdout);
-if (result.stderr) process.stderr.write(result.stderr);
-process.exit(result.status ?? 1);

package/src/scripts/eval/eval-in-action-cat-shellout-demo.ts

@@ -1,31 +0,0 @@
-import { readFileSync } from 'node:fs';
-import { spawnSync } from 'node:child_process';
-
-const source = readFileSync('src/cli/autoresearch.ts', 'utf-8');
-const stillUsesCatShellout = /execFileSync\('cat',\s*\[runtime\.manifestFile\]/.test(source);
-
-if (stillUsesCatShellout) {
-  process.stderr.write('Evaluator: src/cli/autoresearch.ts still shells out to cat for the manifest.\n');
-  process.stdout.write(JSON.stringify({ pass: false, score: 0 }));
-  process.exit(1);
-}
-
-const build = spawnSync('npm', ['run', 'build'], { encoding: 'utf-8' });
-if (build.stdout) process.stderr.write(build.stdout);
-if (build.stderr) process.stderr.write(build.stderr);
-if (build.status !== 0) {
-  process.stdout.write(JSON.stringify({ pass: false, score: 0 }));
-  process.exit(build.status ?? 1);
-}
-
-const test = spawnSync('node', [
-  '--test',
-  'dist/cli/__tests__/autoresearch.test.js',
-  'dist/autoresearch/__tests__/runtime.test.js',
-], { encoding: 'utf-8' });
-if (test.stdout) process.stderr.write(test.stdout);
-if (test.stderr) process.stderr.write(test.stderr);
-
-const pass = test.status === 0;
-process.stdout.write(JSON.stringify({ pass, score: pass ? 1 : 0 }));
-process.exit(test.status ?? 1);

package/src/scripts/eval/eval-ml-kaggle-model-optimization.py

@@ -1,29 +0,0 @@
-from __future__ import annotations
-
-import json
-import subprocess
-import sys
-
-result = subprocess.run(
-    [sys.executable, "playground/ml_kaggle_demo/train.py"],
-    check=False,
-    capture_output=True,
-    text=True,
-)
-
-if result.stdout:
-    sys.stderr.write(result.stdout)
-if result.stderr:
-    sys.stderr.write(result.stderr)
-
-if result.returncode != 0:
-    print(json.dumps({"pass": False, "score": 0.0}))
-    raise SystemExit(result.returncode)
-
-metrics = json.loads(result.stdout)
-auc = float(metrics["roc_auc"])
-
-# Baseline should pass, but score_improvement should still reward better architectures.
-passed = auc >= 0.90
-print(json.dumps({"pass": passed, "score": auc}))
-raise SystemExit(0 if passed else 1)

package/src/scripts/eval/eval-noisy-bayesopt-highdim.py

@@ -1,44 +0,0 @@
-from __future__ import annotations
-
-import json
-import subprocess
-import sys
-from pathlib import Path
-
-CONFIG_PATH = Path('playground/bayesopt_highdim_demo/config.json')
-SEEDS = (17, 29, 43)
-
-
-def run_for_seed(seed: int) -> dict:
-    config = json.loads(CONFIG_PATH.read_text())
-    config['seed'] = seed
-    tmp_path = Path('.rcs') / 'tmp' / f'noisy-bayesopt-seed-{seed}.json'
-    tmp_path.parent.mkdir(parents=True, exist_ok=True)
-    tmp_path.write_text(json.dumps(config))
-
-    result = subprocess.run(
-        [sys.executable, 'playground/bayesopt_highdim_demo/run_search.py', '--config', str(tmp_path)],
-        check=False,
-        capture_output=True,
-        text=True,
-    )
-    if result.stdout:
-        sys.stderr.write(result.stdout)
-    if result.stderr:
-        sys.stderr.write(result.stderr)
-    if result.returncode != 0:
-        raise SystemExit(result.returncode)
-    return json.loads(result.stdout)
-
-
-def main() -> None:
-    rows = [run_for_seed(seed) for seed in SEEDS]
-    means = [float(row['best_mean']) for row in rows]
-    overall_mean = sum(means) / len(means)
-    variance_penalty = (max(means) - min(means)) * 0.15
-    score = overall_mean - variance_penalty
-    print(json.dumps({'pass': score >= 1.15, 'score': score}))
-
-
-if __name__ == '__main__':
-    main()

package/src/scripts/eval/eval-noisy-latent-subspace-discovery.py

@@ -1,44 +0,0 @@
-from __future__ import annotations
-
-import json
-import subprocess
-import sys
-from pathlib import Path
-
-CONFIG_PATH = Path('playground/bayesopt_latent_discovery_demo/config.json')
-SEEDS = (23, 41, 59)
-
-
-def run_for_seed(seed: int) -> dict:
-    config = json.loads(CONFIG_PATH.read_text())
-    config['seed'] = seed
-    tmp_path = Path('.rcs') / 'tmp' / f'latent-discovery-seed-{seed}.json'
-    tmp_path.parent.mkdir(parents=True, exist_ok=True)
-    tmp_path.write_text(json.dumps(config))
-
-    result = subprocess.run(
-        [sys.executable, 'playground/bayesopt_latent_discovery_demo/run_search.py', '--config', str(tmp_path)],
-        check=False,
-        capture_output=True,
-        text=True,
-    )
-    if result.stdout:
-        sys.stderr.write(result.stdout)
-    if result.stderr:
-        sys.stderr.write(result.stderr)
-    if result.returncode != 0:
-        raise SystemExit(result.returncode)
-    return json.loads(result.stdout)
-
-
-def main() -> None:
-    rows = [run_for_seed(seed) for seed in SEEDS]
-    means = [float(row['best_mean']) for row in rows]
-    overall_mean = sum(means) / len(means)
-    variance_penalty = (max(means) - min(means)) * 0.18
-    score = overall_mean - variance_penalty
-    print(json.dumps({'pass': score >= 1.4, 'score': score}))
-
-
-if __name__ == '__main__':
-    main()

package/src/scripts/eval/eval-parity-smoke.ts

@@ -1,20 +0,0 @@
-import { spawnSync } from 'node:child_process';
-
-const build = spawnSync('npm', ['run', 'build'], { encoding: 'utf-8' });
-if (build.stdout) process.stderr.write(build.stdout);
-if (build.stderr) process.stderr.write(build.stderr);
-if (build.status !== 0) {
-  process.stdout.write(JSON.stringify({ pass: false }));
-  process.exit(build.status ?? 1);
-}
-
-const test = spawnSync('node', [
-  '--test',
-  'dist/autoresearch/__tests__/contracts.test.js',
-  'dist/autoresearch/__tests__/runtime.test.js',
-  'dist/cli/__tests__/autoresearch.test.js',
-], { encoding: 'utf-8' });
-if (test.stdout) process.stderr.write(test.stdout);
-if (test.stderr) process.stderr.write(test.stderr);
-process.stdout.write(JSON.stringify({ pass: test.status === 0 }));
-process.exit(test.status ?? 1);

package/src/scripts/eval/eval-parity-sweep.ts

@@ -1,26 +0,0 @@
-import { spawnSync } from 'node:child_process';
-
-const build = spawnSync('npm', ['run', 'build'], { encoding: 'utf-8' });
-if (build.stdout) process.stderr.write(build.stdout);
-if (build.stderr) process.stderr.write(build.stderr);
-if (build.status !== 0) {
-  process.stdout.write(JSON.stringify({ pass: false }));
-  process.exit(build.status ?? 1);
-}
-
-const testArgs = [
-  '--test',
-  'dist/cli/__tests__/autoresearch.test.js',
-  'dist/cli/__tests__/index.test.js',
-  'dist/cli/__tests__/nested-help-routing.test.js',
-  'dist/cli/__tests__/session-search-help.test.js',
-  'dist/autoresearch/__tests__/contracts.test.js',
-  'dist/autoresearch/__tests__/runtime.test.js',
-  'dist/team/__tests__/worktree.test.js',
-  'dist/modes/__tests__/base-autoresearch-contract.test.js',
-];
-const test = spawnSync('node', testArgs, { encoding: 'utf-8' });
-if (test.stdout) process.stderr.write(test.stdout);
-if (test.stderr) process.stderr.write(test.stderr);
-process.stdout.write(JSON.stringify({ pass: test.status === 0 }));
-process.exit(test.status ?? 1);

package/src/scripts/eval/eval-resume-dirty-guard.ts

@@ -1,8 +0,0 @@
-import { spawnSync } from 'node:child_process';
-const result = spawnSync('node', ['--test', 'dist/cli/__tests__/autoresearch.test.js', 'dist/autoresearch/__tests__/runtime.test.js'], {
-  encoding: 'utf-8',
-});
-process.stdout.write(JSON.stringify({ pass: result.status === 0 }));
-if (result.stdout) process.stderr.write(result.stdout);
-if (result.stderr) process.stderr.write(result.stderr);
-process.exit(result.status ?? 1);

package/src/scripts/eval/eval-security-path-traversal.ts

@@ -1,38 +0,0 @@
-#!/usr/bin/env node
-import { spawnSync } from 'node:child_process';
-
-const checks: [string, string[]][] = [
-  ['node', ['--test', 'dist/mcp/__tests__/path-traversal.test.js']],
-  ['node', ['--test', 'dist/mcp/__tests__/state-paths.test.js']],
-];
-
-function run(command: string, args: string[]) {
-  const result = spawnSync(command, args, {
-    encoding: 'utf-8',
-    stdio: ['ignore', 'pipe', 'pipe'],
-  });
-  return {
-    command: [command, ...args].join(' '),
-    status: result.status ?? 1,
-    stdout: (result.stdout || '').trim(),
-    stderr: (result.stderr || '').trim(),
-  };
-}
-
-const build = run('npm', ['run', 'build']);
-const results = [build, ...checks.map(([command, args]) => run(command, args))];
-const passed = results.filter((result) => result.status === 0).length;
-const score = Number((passed / results.length).toFixed(2));
-const pass = results.every((result) => result.status === 0);
-
-console.log(JSON.stringify({
-  pass,
-  score,
-  summary: 'Security path-traversal pilot evaluator',
-  details: results.map(({ command, status, stderr }) => ({
-    command,
-    ok: status === 0,
-    status,
-    stderr: stderr || undefined,
-  })),
-}));

package/src/scripts/run-autoresearch-showcase.sh

@@ -1,75 +0,0 @@
-#!/usr/bin/env bash
-set -euo pipefail
-
-show_usage() {
-  cat <<'USAGE'
-Usage:
-  scripts/run-autoresearch-showcase.sh --list
-  scripts/run-autoresearch-showcase.sh <showcase> [<showcase> ...]
-
-Available showcases:
-  rcs-self       -> missions/in-action-cat-shellout-demo
-  ml-tabular     -> missions/ml-kaggle-model-optimization
-  bayesopt       -> missions/noisy-bayesopt-highdim
-  latent         -> missions/noisy-latent-subspace-discovery
-  sorting        -> missions/adaptive-sort-optimization
-  all            -> rcs-self ml-tabular bayesopt latent sorting
-
-Examples:
-  scripts/run-autoresearch-showcase.sh --list
-  scripts/run-autoresearch-showcase.sh bayesopt
-  scripts/run-autoresearch-showcase.sh rcs-self ml-tabular
-USAGE
-}
-
-mission_for() {
-  case "$1" in
-    rcs-self)   printf '%s' 'missions/in-action-cat-shellout-demo' ;;
-    ml-tabular) printf '%s' 'missions/ml-kaggle-model-optimization' ;;
-    bayesopt)   printf '%s' 'missions/noisy-bayesopt-highdim' ;;
-    latent)     printf '%s' 'missions/noisy-latent-subspace-discovery' ;;
-    sorting)    printf '%s' 'missions/adaptive-sort-optimization' ;;
-    *) return 1 ;;
-  esac
-}
-
-list_showcases() {
-  cat <<'LIST'
-rcs-self   missions/in-action-cat-shellout-demo
-ml-tabular missions/ml-kaggle-model-optimization
-bayesopt   missions/noisy-bayesopt-highdim
-latent     missions/noisy-latent-subspace-discovery
-sorting    missions/adaptive-sort-optimization
-LIST
-}
-
-if [[ $# -eq 0 ]]; then
-  show_usage
-  exit 1
-fi
-
-if [[ "$1" == "--help" || "$1" == "-h" ]]; then
-  show_usage
-  exit 0
-fi
-
-if [[ "$1" == "--list" ]]; then
-  list_showcases
-  exit 0
-fi
-
-args=("$@")
-if [[ " ${args[*]} " == *" all "* ]]; then
-  args=(rcs-self ml-tabular bayesopt latent sorting)
-fi
-
-for showcase in "${args[@]}"; do
-  mission="$(mission_for "$showcase")" || {
-    printf 'Unknown showcase: %s\n\n' "$showcase" >&2
-    show_usage >&2
-    exit 1
-  }
-
-  printf '\n==> Running showcase %s (%s)\n' "$showcase" "$mission"
-  rcs autoresearch "$mission"
-done