sno-ai/sno-station-skills / skills/R-recursive-self-improvement/rem-reflect/skill
rem-reflect
VerifiedSelf 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.
scripts/proposer-loop.test.ts
View on GitHubimport { test } from 'node:test';
import assert from 'node:assert/strict';
import { existsSync, unlinkSync } from 'node:fs';
import { join } from 'node:path';
import { run, main } from './rem-reflect.ts';
import { git } from './store.ts';
import { tmp, makeConfig, makeStore, FixtureBackend, fixtureHarnessHomes } from './test-helpers.ts';
// Cloud proposal generation is exercised in the cloud service's integration tests;
// local cloud-answer staging and stale-target refusal are exercised in cloud-apply.test.ts.
test('a run with config.json deleted exits non-zero before the lock, with no commit', () => {
const { claudeHome, codexHome } = fixtureHarnessHomes(['heartbeat']);
const config = makeConfig({ claude_home: claudeHome, codex_home: codexHome,
claude_root: tmp('c'), codex_root: tmp('x') });
const store = makeStore(config);
const commitsBefore = git(store, ['log', '--format=%s']).trim().split('\n').length;
unlinkSync(join(store, 'config.json'));
assert.throws(() => run(store, new Date('2026-09-08T00:00:00Z'), 'u', new FixtureBackend()), /config\.json/);
assert.equal(existsSync(join(store, '.lock')), false);
const previous = process.env.REM_REFLECT_STORE;
process.env.REM_REFLECT_STORE = store;
try { assert.equal(main(['run']), 1); }
finally { if (previous === undefined) delete process.env.REM_REFLECT_STORE; else process.env.REM_REFLECT_STORE = previous; }
assert.equal(git(store, ['log', '--format=%s']).trim().split('\n').length, commitsBefore);
});
Related skills
| Skill | Stars | Updated | Works with | Status | Install |
|---|---|---|---|---|---|
| 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: 472k | Updated | Claude CodeCodex | Unverified | Install |
| 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: 322k | Updated | Claude CodeCodex | Verified | Install |
| dispatching-parallel-agentsobra/superpowersUse when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |
| 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 available | Stars: 322k | Updated | Claude CodeCodex | Verified | Install |