Skip to content

sno-ai/sno-station-skills / skills/R-recursive-self-improvement/rem-reflect/skill

rem-reflect

Verified

Self Learning from this machine's Claude Code, Codex, Hermes, OpenClaw and Cursor sessions. Decide skill changes and lessons with accept/reject/tbd; recall lessons at session start.

FileKindSize
SKILL.mdskill md14.1 KB
references/labeler.mdmarkdown1.2 KB
references/labeler.schema.jsonconfig1.7 KB
references/local-settings.jsonconfig126 B
references/local-writer.schema.jsonconfig2.3 KB
references/proposal.schema.jsonconfig3.2 KB
references/render.jsonconfig245 B
references/signals.jsonconfig71 B
references/text.jsonconfig4.0 KB
scripts/adopt.test.tsscript13.0 KB
scripts/adopt.tsscript14.3 KB
scripts/agent-sessions.tsscript9.1 KB
scripts/allowance-fallback.test.tsscript16.0 KB
scripts/allowance-request-isolation.test.tsscript7.1 KB
scripts/backend.tsscript9.1 KB
scripts/calls.tsscript8.6 KB
scripts/catalogue-cloud.test.tsscript1.5 KB
scripts/catalogue.tsscript3.2 KB
scripts/chunk.tsscript2.1 KB
scripts/cloud-apply.test.tsscript25.2 KB
scripts/cloud-batch.test.tsscript11.2 KB
scripts/cloud-day.test.tsscript6.8 KB
scripts/cloud-verdict.test.tsscript12.1 KB
scripts/cloud-wait.test.tsscript1.3 KB
scripts/cloud.tsscript24.4 KB
scripts/config.tsscript8.1 KB
scripts/cursor.test.tsscript16.1 KB
scripts/cursor.tsscript6.7 KB
scripts/evidence.tsscript1.5 KB
scripts/first-message.test.tsscript10.3 KB
scripts/harvest.test.tsscript16.5 KB
scripts/harvest.tsscript22.6 KB
scripts/hermes-openclaw.test.tsscript25.6 KB
scripts/identity.test.tsscript3.3 KB
scripts/identity.tsscript3.5 KB
scripts/installed-roots.test.tsscript11.0 KB
scripts/journey-adopt-lesson.test.tsscript4.1 KB
scripts/journey-ops.test.tsscript8.0 KB
scripts/labeler.test.tsscript3.6 KB
scripts/labeler.tsscript9.5 KB
scripts/ledger.tsscript2.1 KB
scripts/lessons.tsscript4.7 KB
scripts/local-filter.test.tsscript3.9 KB
scripts/local-first-output.test.tsscript23.5 KB
scripts/local-settings.tsscript1.4 KB
scripts/local-writer.tsscript12.7 KB
scripts/login-in-place.test.tsscript5.8 KB
scripts/model-json.tsscript4.1 KB
scripts/no-network.test.tsscript5.0 KB
scripts/observe.tsscript1.4 KB
scripts/page-journey.test.tsscript6.7 KB
scripts/pages.test.tsscript4.1 KB
scripts/pages.tsscript4.8 KB
scripts/proposer-loop.test.tsscript1.5 KB
scripts/proposer-validate.test.tsscript9.1 KB
scripts/proposer.tsscript8.7 KB
scripts/recall-hook.test.tsscript20.9 KB
scripts/recall.test.tsscript31.4 KB
scripts/recall.tsscript18.2 KB
scripts/reflect.test.tsscript9.3 KB
scripts/reflect.tsscript14.3 KB
scripts/rem-reflectexecutablescript823 B
scripts/rem-reflect.tsscript17.8 KB
scripts/render-chunk.test.tsscript7.2 KB
scripts/render.tsscript9.7 KB
scripts/report.tsscript8.2 KB
scripts/run-status.test.tsscript19.1 KB
scripts/sampling.test.tsscript2.1 KB
scripts/sampling.tsscript915 B
scripts/selftest-guard.test.tsscript4.2 KB
scripts/selftest/bin/claudeexecutablescript94 B
scripts/selftest/bin/codexexecutablescript93 B
scripts/selftest/bin/shim-core.cjsscript4.6 KB
scripts/selftest/bin/snoexecutablescript5.7 KB
scripts/selftest/fixtures/hermes-session-export.jsonlother1.5 KB
scripts/selftest/fixtures/openclaw-events.jsonlother3.7 KB
scripts/selftest/fixtures/verdict-traces.jsonconfig16.6 KB
scripts/selftest/journey-e2e.shexecutablescript1.4 KB
scripts/selftest/journey.mjsscript9.5 KB
scripts/selftest/observe-journey.mjsscript12.5 KB
scripts/selftest/run-selftest.shexecutablescript7.0 KB
scripts/selftest/spawn-python.mjsexecutablescript765 B
scripts/session.test.tsscript5.2 KB
scripts/session.tsscript251 B
scripts/signal-local.test.tsscript7.0 KB
scripts/skill-impact.test.tsscript6.2 KB
scripts/station-settings.test.tsscript13.6 KB
scripts/store-memory.test.tsscript3.4 KB
scripts/store.tsscript7.7 KB
scripts/test-helpers.tsscript15.3 KB
scripts/text.tsscript760 B
scripts/trigger.test.tsscript3.6 KB
scripts/trigger.tsscript2.5 KB
scripts/verdicts.test.tsscript8.1 KB
scripts/verdicts.tsscript8.0 KB

scripts/signal-local.test.ts

View on GitHub
import { test } from 'node:test';
import assert from 'node:assert/strict';
import { mkdirSync, writeFileSync } from 'node:fs';
import { join } from 'node:path';
import { buildCloudBatch } from './cloud.ts';
import { labelHalf } from './labeler.ts';
import { renderTrace, loadRenderBudgets } from './render.ts';
import { fixtureConfig, makeStore } from './test-helpers.ts';
import type { Trace } from './harvest.ts';

function trace(agent: 'codex' | 'claude-code', records: Trace['records']): Trace {
  return { user_id: 'u', project_id: 'p', agent_id: agent, source_harness: agent, originator: agent,
    trace_id: 's.v1', session_id: 's', version: 1, source_path: '/source', source_line_range: [1, records.length + 1],
    source_mtime: 1, records, skipped_records: 0, skipped_blocks: 0, redactions: 0, trivial: false, skills_loaded: [] };
}
function batch(row: Trace): { calls: Record<string, unknown>[] } {
  const config = fixtureConfig();
  const store = makeStore(config);
  const labels = new Map([['u/' + row.agent_id + '/s.v1', { decision: 'keep' as const, outcome: 'fail' as const,
    reason: 'failed', evidence: [], key_ranges: [], labeled_by: 'codex', model: 'local' }]]);
  return buildCloudBatch(store, config, 'run', [row], labels, false).halves[0].sessions[0] as { calls: Record<string, unknown>[] };
}

test('Codex command and failed script reach the batch with literal failure facts', () => {
  const row = trace('codex', [
    { line_number: 2, source_line: 2, record: { type: 'response_item', timestamp: '2026-09-09T20:00:00Z', payload: {
      type: 'custom_tool_call', call_id: 'call-1', name: 'exec', input: 'patch file' } } },
    { line_number: 3, source_line: 3, record: { type: 'event_msg', payload: { type: 'item_completed', turn_id: 'turn-1',
      started_at_ms: 1788984000000, completed_at_ms: 1788984001000, item: { type: 'CommandExecution', id: 'exec-1',
        parsed_cmd: [{ cmd: 'false' }], status: 'failed', exit_code: 1, aggregated_output: 'bad command' } } } },
    { line_number: 4, source_line: 4, record: { type: 'response_item', timestamp: '2026-09-09T20:00:02Z', payload: {
      type: 'custom_tool_call_output', call_id: 'call-1', output: [{ type: 'input_text', text: 'Script failed\nScript error:\napply_patch verification failed' }] } } },
  ]);
  const calls = batch(row).calls;
  assert.equal(calls.length, 2);
  assert.deepEqual(calls.map(call => [call.call_id, call.failed, call.failure_kind, call.exit_code]),
    [['exec-1', true, 'exit_nonzero', 1], ['call-1', true, 'edit_mismatch', null]]);
  assert.match(renderTrace(row, loadRenderBudgets()).body, /3: command false exit 1 bad command/);
  assert.match(renderTrace(row, loadRenderBudgets()).body, /4: custom_tool_call_output Script failed/);
});

test('a script failure returned by wait keeps the original script call id', () => {
  const row = trace('codex', [
    { line_number: 2, source_line: 2, record: { type: 'response_item', payload: {
      type: 'custom_tool_call', call_id: 'call-2', input: 'apply a patch' } } },
    { line_number: 3, source_line: 3, record: { type: 'response_item', payload: {
      type: 'custom_tool_call_output', call_id: 'call-2', output: [{ type: 'input_text', text: 'Script running with cell ID 42' }] } } },
    { line_number: 4, source_line: 4, record: { type: 'response_item', payload: {
      type: 'function_call', call_id: 'wait-1', name: 'wait', arguments: '{"cell_id":"42"}' } } },
    { line_number: 5, source_line: 5, record: { type: 'response_item', payload: {
      type: 'function_call_output', call_id: 'wait-1', output: 'Script failed\napply_patch verification failed' } } },
  ]);
  assert.deepEqual(batch(row).calls.map(call => [call.call_id, call.line_start, call.line_end, call.failure_kind]),
    [['call-2', 2, 5, 'edit_mismatch']]);
});

test('Claude benign nonzero stays successful and injected notification is marked', () => {
  const row = trace('claude-code', [
    { line_number: 2, source_line: 2, record: { type: 'assistant', timestamp: '2026-09-09T20:00:00Z',
      message: { role: 'assistant', content: [{ type: 'tool_use', id: 'toolu-1', name: 'Bash', input: { command: 'grep x file' } }] } } },
    { line_number: 3, source_line: 3, record: { type: 'user', timestamp: '2026-09-09T20:00:01Z', promptId: 'turn-1',
      toolUseResult: { returnCodeInterpretation: 'no match' }, message: { role: 'user', content: [
        { type: 'tool_result', tool_use_id: 'toolu-1', content: 'Exit code 1\nno match', is_error: false }] } } },
    { line_number: 4, source_line: 4, record: { type: 'user', message: { role: 'user', content: '<task-notification>done</task-notification>' } } },
    { line_number: 5, source_line: 5, record: { type: 'user', isMeta: true, message: { role: 'user', content: 'Base directory for this skill: /skills/x' } } },
    { line_number: 6, source_line: 6, record: { type: 'user', message: { role: 'user', content: 'please stop' } } },
    { line_number: 7, source_line: 7, record: { type: 'user', isCompactSummary: true, message: { role: 'user', content: 'This session is being continued' } } },
  ]);
  assert.deepEqual(batch(row).calls.map(call => [call.failed, call.benign_nonzero, call.exit_code]), [[false, true, 1]]);
  const body = renderTrace(row, loadRenderBudgets()).body;
  assert.match(body, /4: user \[harness-shaped\] <task-notification>/);
  assert.match(body, /5: user \[harness-shaped\] Base directory/);
  assert.match(body, /6: user please stop/);
  assert.match(body, /7: user \[harness-shaped\] This session/);
});

test('labeling starts with the session that has more failures and typed owner messages across harnesses', () => {
  const claude = { ...trace('claude-code', [{ line_number: 2, source_line: 2, record: {
    type: 'user', message: { role: 'user', content: 'please help' } } }]), trace_id: 'claude.v1', session_id: 'claude' };
  const codex = { ...trace('codex', [
    { line_number: 2, source_line: 2, record: { type: 'response_item', payload: {
      type: 'message', role: 'user', content: [{ type: 'input_text', text: 'fix it' }] } } },
    { line_number: 3, source_line: 3, record: { type: 'event_msg', payload: { type: 'item_completed', turn_id: 'turn',
      item: { type: 'CommandExecution', id: 'exec-1', parsed_cmd: [{ cmd: 'false' }], status: 'failed',
        exit_code: 1, aggregated_output: 'failed' } } } },
  ]), trace_id: 'codex.v1', session_id: 'codex' };
  const store = makeStore(fixtureConfig());
  const raw = join(store, 'raw');
  mkdirSync(raw, { recursive: true });
  writeFileSync(join(raw, 'claude.v1.json'), JSON.stringify(claude));
  writeFileSync(join(raw, 'codex.v1.json'), JSON.stringify(codex));
  const ordered: string[] = [];
  const backend = { preflight: () => true,
    spawn: ({ input }: { input: string }) => {
      ordered.push(/"trace_id":"([^"]+)"/.exec(input)?.[1] ?? 'missing');
      return { stdout: JSON.stringify({ decision: 'keep', outcome: 'fail', reason: 'failure', evidence: [], key_ranges: [], notes: '' }) };
    } };
  const result = labelHalf(store, 'run', null, null, [claude, codex], backend, [], [claude, codex]);
  assert.deepEqual(ordered, ['codex.v1', 'claude.v1']);
  assert.equal(result.writes.length, 2);
});
reverse-engineer-anythingmorluto/reaReverse engineer native, managed, Electron/JavaScript, packaged, firmware, and browser targets with REA, and build agent environments (AgentEnv bundles) of web applications from a live instance or a capture, and of Linux desktop apps with a task from a request. Use shipped-artifact or requested runtime evidence to explain features, compare versions, decompile code, or guide a reconstruction. Skip REA for ordinary source-repository architecture analysis.Stars: 472kUpdated Claude CodeCodexVerifiedInstall
diagnosing-superpowersobra/superpowersUse when a superpowers session went wrong and your human partner wants to know why — repeated work, ignored plans, stumbles, poor results, a skill that didn't fire, "it took too long", "why is it so expensive", "what is it doing" — or wants to build a bug report for the superpowers maintainers, for the current session or a past one identified by id or path, on any harness.Stars: 323kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 323kUpdated Claude CodeCodexVerifiedInstall
executing-plansobra/superpowersUse when executing an implementation plan in the current session as the implementer yourself — your human partner chose inline execution, or no subagent tool is availableStars: 323kUpdated Claude CodeCodexVerifiedInstall