/SKILL.md
AI context persistence - tags in code = permanent memory across sessions
npx skillsauth add bitjaru/codesyncer codesyncerInstall this skill globally with one command. Works with Claude Code, Cursor, and Windsurf.
3 of 9 scanners reported clean
Some scanners were skipped, did not run, or reported a non-clean status. Review each row below.
Claude forgets everything when the session ends. CodeSyncer makes it remember.
Use this skill on ANY project where you want AI to:
| Situation | Tag | Example |
|-----------|-----|---------|
| You inferred something | @codesyncer-inference | // @codesyncer-inference: Page size 20 (standard UX) |
| Decision after discussion | @codesyncer-decision | // @codesyncer-decision: [2024-01-15] Using JWT |
| Non-standard implementation | @codesyncer-rule | // @codesyncer-rule: any type here (no types available) |
| Needs user confirmation | @codesyncer-todo | // @codesyncer-todo: Confirm API endpoint |
| Business context | @codesyncer-context | // @codesyncer-context: GDPR requires 30-day retention |
ALWAYS ASK the user about:
❌ Bad: "I set the shipping fee to $5"
✅ Good: "What should the shipping fee be?"
When you detect these keywords, STOP and discuss before coding:
// @codesyncer-decision: [2024-01-15] Using Stripe for payments (international support)
// @codesyncer-context: Supports USD, EUR, KRW currencies
const paymentProvider = 'stripe';
// @codesyncer-inference: 5 second timeout (typical API response time)
// @codesyncer-rule: Retry max 3 times (rate limit protection)
const apiConfig = {
timeout: 5000,
retries: 3,
};
// @codesyncer-todo: Confirm discount percentage with business team
const DISCOUNT_RATE = 0.1; // 10%
Next session, when AI reads your code:
@codesyncer-decision → Knows WHY you chose Stripe@codesyncer-inference → Knows the reasoning behind values@codesyncer-todo → Knows what still needs confirmationContext survives across sessions. No more "why did we do this?"
Inferred something? → @codesyncer-inference: [reason]
Made a decision? → @codesyncer-decision: [date] [what] [why]
Special rule? → @codesyncer-rule: [explanation]
Need to confirm? → @codesyncer-todo: [what to confirm]
Business context? → @codesyncer-context: [domain knowledge]
development
Maintainer-only workflow for handling GitHub Secret Scanning alerts on OpenClaw. Use when Codex needs to triage, redact, clean up, and resolve secret leakage found in issue comments, issue bodies, PR comments, or other GitHub content.
development
Maintainer workflow for OpenClaw releases, prereleases, changelog release notes, and publish validation. Use when Codex needs to prepare or verify stable or beta release steps, align version naming, assemble release notes, check release auth requirements, or validate publish-time commands and artifacts.
development
Run, watch, debug, and extend OpenClaw QA testing with qa-lab and qa-channel. Use when Codex needs to execute the repo-backed QA suite, inspect live QA artifacts, debug failing scenarios, add new QA scenarios, or explain the OpenClaw QA workflow. Prefer the live OpenAI lane with regular openai/gpt-5.4 in fast mode; do not use gpt-5.4-pro or gpt-5.4-mini unless the user explicitly overrides that policy.
development
End-to-end Parallels smoke, upgrade, and rerun workflow for OpenClaw across macOS, Windows, and Linux guests. Use when Codex needs to run, rerun, debug, or interpret VM-based install, onboarding, gateway smoke tests, latest-release-to-main upgrade checks, fresh snapshot retests, or optional Discord roundtrip verification under Parallels.