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.tsscript22.1 KB
scripts/local-settings.tsscript1.4 KB
scripts/local-writer.tsscript12.6 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/cloud-day.test.ts

View on GitHub
import { test } from 'node:test';
import assert from 'node:assert/strict';
import { chmodSync, existsSync, readFileSync, writeFileSync } from 'node:fs';
import { join } from 'node:path';
import { run } from './rem-reflect.ts';
import { readState } from './store.ts';
import { FixtureBackend, fixtureConfig, makeStore, tmp, writeStationSettings,
  writeCodexSession, codexMeta, codexUser, codexAssistant } from './test-helpers.ts';

test('daily sharing follows mode, only enhanced reports cloud judgments, and rejected sends preserve the local report', t => {
  const bin = tmp('sno-cloud-day');
  const executable = join(bin, 'sno');
  writeFileSync(executable, [
    '#!/usr/bin/env node',
    "const fs = require('node:fs');",
    "const args = process.argv.slice(2).join(' ');",
    "if (args === 'skills rem-reflect-local-writer') { console.log('Find one lesson worth keeping and answer as JSON.'); process.exit(0); }",
    "if (args !== 'rem judge --json') { console.error('unexpected sno command: ' + args); process.exit(2); }",
    "const input = fs.readFileSync(0, 'utf8');",
    "fs.writeFileSync(process.env.REM_REQUEST_CAPTURE, input);",
    "if (process.env.REM_TEST_CONSENT !== 'full') { console.error('upload rejected: consent ' + process.env.REM_TEST_CONSENT); process.exit(1); }",
    "if (process.env.REM_TEST_FAIL === '1') { console.error('temporary cloud outage'); process.exit(1); }",
    "const batch = JSON.parse(input);",
    "const page = {page_id:'cloud-page',summary:'Cloud page judgment',body:'cloud body',root_cause:{fact:'cloud fact'},citations:[],count:1,last_seen:'2026-09-21',superseded:false};",
    "console.log(JSON.stringify({schema_version:1,run_id:batch.run_id,history_acknowledged:true,history_links:[],halves:batch.halves.map(half=>({harness:half.harness,attention:half.sessions.map(session=>({trace_id:session.trace_id,jev_outcome:'success',fail_probability:0.2,basis:'jev'})),pages:[{judgment_id:'j-page',page}],lessons:[],proposals:[],read_judgments:[],log_entry:'Cloud judgment for this run'}))}));",
  ].join('\n') + '\n');
  chmodSync(executable, 0o755);
  const keys = ['PATH', 'SNO_PROFILE_DIR', 'REM_TEST_CONSENT', 'REM_REQUEST_CAPTURE', 'REM_TEST_FAIL'];
  const before = new Map(keys.map(key => [key, process.env[key]]));
  process.env.PATH = `${bin}:${process.env.PATH ?? ''}`;
  t.after(() => {
    for (const [key, value] of before) {
      if (value === undefined) delete process.env[key]; else process.env[key] = value;
    }
  });
  const config = fixtureConfig();
  let nativeReport = '';
  for (const mode of ['agent-native', 'rem-enhanced', 'local-first']) {
    for (const outcome of ['success', 'off', 'metadata-only', 'outage']) {
      process.env.SNO_PROFILE_DIR = writeStationSettings(mode);
      process.env.REM_TEST_CONSENT = outcome === 'off' || outcome === 'metadata-only' ? outcome : 'full';
      process.env.REM_TEST_FAIL = outcome === 'outage' ? '1' : '0';
      const store = makeStore(config);
      writeCodexSession(config.codex_root, 'session',
        [codexMeta('session', '/n'), codexUser('Finish this repair'), codexAssistant('The repair is incomplete')],
        Date.parse('2026-09-20T00:00:00Z'), '2026/09/20', '2026-09-20T00-00-00');
      const capture = join(bin, `request-${mode}-${outcome}.json`);
      process.env.REM_REQUEST_CAPTURE = capture;
      const backend = new FixtureBackend();
      const result = run(store, new Date('2026-09-21T00:00:00Z'), 'u', backend);
      assert.equal(result.code, 0, result.lines.join('\n'));
      assert.equal(readState(store).last_terminal?.status, 'success');
      const report = readFileSync(join(store, 'staging', '20260921-0000', 'REPORT.md'), 'utf8');
      const log = readFileSync(join(store, 'staging', '20260921-0000', 'run.log'), 'utf8');
      if (mode === 'local-first') {
        assert.equal(existsSync(capture), false);
        assert.equal(backend.calls.filter(call => call.kind === 'labeler').length, 0);
        assert.match(report, /No-upload: local-first mode/);
      } else {
        assert.equal(existsSync(capture), true, `${mode} reaches the CLI even when it rejects consent`);
        const batch = JSON.parse(readFileSync(capture, 'utf8'));
        assert.deepEqual(batch.halves.flatMap((half: { sessions: { trace_id: string }[] }) => half.sessions.map(row => row.trace_id)), ['session.v1']);
        assert.equal(backend.calls.filter(call => call.kind === 'labeler').length, 1);
        if (mode === 'agent-native') {
          if (outcome === 'success') nativeReport = report;
          assert.equal(report, nativeReport, 'sending cannot alter the native local report');
          assert.doesNotMatch(report, /Cloud judgment|Cloud-ranked|predicted success/);
          assert.equal(existsSync(join(store, 'wiki', 'patterns', 'cloud-page.md')), false, 'native does not apply the cloud judgment');
        } else if (outcome === 'success') {
          assert.match(report, /Cloud judgment for this run/);
          assert.match(report, /Cloud-ranked: 1/);
          assert.match(readFileSync(join(store, 'wiki', 'patterns', 'cloud-page.md'), 'utf8'), /Cloud page judgment/);
          assert.match(report, /session\.v1: predicted success/);
        } else {
          assert.match(report, /Local session outcomes:[\s\S]*session\.v1: fail/);
          assert.doesNotMatch(report, /Cloud judgment|Cloud-ranked|Run .* failed/);
        }
        if (outcome !== 'success') {
          assert.match(log, /cloud run 20260921-0000 send failed: .*?(upload rejected: consent|temporary cloud outage)/);
          assert.doesNotMatch(report, /send failed|upload rejected|cloud outage/);
        }
      }
    }
  }
});

test('an empty completed run is sent through the ordinary daily entry', t => {
  const capture = join(tmp('empty-day'), 'request.json');
  const bin = tmp('empty-cli');
  writeFileSync(join(bin, 'sno'), `#!/usr/bin/env node
const fs = require('node:fs');
const batch = JSON.parse(fs.readFileSync(0, 'utf8'));
fs.writeFileSync(process.env.REM_REQUEST_CAPTURE, JSON.stringify(batch));
console.log(JSON.stringify({schema_version:1,run_id:batch.run_id,history_acknowledged:true,history_links:[],halves:[]}));
`, { mode: 0o755 });
  const before = { PATH: process.env.PATH, SNO_PROFILE_DIR: process.env.SNO_PROFILE_DIR, REM_REQUEST_CAPTURE: process.env.REM_REQUEST_CAPTURE };
  Object.assign(process.env, { PATH: `${bin}:${process.env.PATH ?? ''}`, SNO_PROFILE_DIR: writeStationSettings('agent-native'), REM_REQUEST_CAPTURE: capture });
  t.after(() => { for (const [key, value] of Object.entries(before)) { if (value === undefined) delete process.env[key]; else process.env[key] = value; } });
  const store = makeStore(fixtureConfig());
  const result = run(store, new Date('2026-09-21T00:00:00Z'), 'u', new FixtureBackend());
  assert.equal(result.code, 0, result.lines.join('\n'));
  const batch = JSON.parse(readFileSync(capture, 'utf8'));
  assert.equal(batch.run_id, '20260921-0000');
  assert.deepEqual(batch.halves, []);
});
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 CodeCodexUnverifiedInstall
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: 322kUpdated Claude CodeCodexVerifiedInstall
dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependenciesStars: 322kUpdated 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: 322kUpdated Claude CodeCodexVerifiedInstall