with one click
verification-loop
A comprehensive verification system for Claude Code sessions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Menu
A comprehensive verification system for Claude Code sessions.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Transform Claude Code into a fully autonomous agent system with persistent memory, scheduled operations, computer use, and task queuing. Replaces standalone agent frameworks (Hermes, AutoGPT) by leveraging Claude Code's native crons, dispatch, MCP tools, and memory. Use when the user wants continuous autonomous operation, scheduled tasks, or a self-directing agent loop.
Scan spec docs and synchronize .claude/ontology/index.json with docs/features/index.md. Use when adding a new domain, editing spec files, or when CI validate-ontology fails.
Automatically extract reusable patterns from Claude Code sessions and save them as learned skills for future use.
Patterns and architectures for autonomous Claude Code loops โ from simple sequential pipelines to RFC-driven multi-agent DAG systems.
Persistent per-project memory for Claude Code. Auto-loads project context on session start, tracks sessions with git activity, and writes to native memory. Commands run deterministic Node.js scripts โ behavior is consistent across model versions.
Instinct-based learning system that observes sessions via hooks, creates atomic instincts with confidence scoring, and evolves them into skills/commands/agents. v2.1 adds project-scoped instincts to prevent cross-project contamination.
| name | verification-loop |
| description | A comprehensive verification system for Claude Code sessions. |
| origin | ECC |
A comprehensive verification system for Claude Code sessions.
Invoke this skill:
# Check if project builds
npm run build 2>&1 | tail -20
# OR
pnpm build 2>&1 | tail -20
If build fails, STOP and fix before continuing.
# TypeScript projects
npx tsc --noEmit 2>&1 | head -30
# Python projects
pyright . 2>&1 | head -30
Report all type errors. Fix critical ones before continuing.
# JavaScript/TypeScript
npm run lint 2>&1 | head -30
# Python
ruff check . 2>&1 | head -30
# Run tests with coverage
npm run test -- --coverage 2>&1 | tail -50
# Check coverage threshold
# Target: 80% minimum
Report:
.claude/ontology/index.json์ด ์๋ ๊ฒฝ์ฐ(์ต์
):
if [ -f .claude/ontology/index.json ] && [ -f scripts/ci/validate-ontology.js ]; then
PLUGIN_ROOT="${CLAUDE_PLUGIN_ROOT:-${CODEX_PLUGIN_ROOT:-$(cat "$HOME/.claude/.omf-root" 2>/dev/null || echo "$HOME/.claude")}}"
node "$PLUGIN_ROOT/scripts/ci/validate-ontology.js" && echo "ontology OK" || echo "FAIL: ontology ๋ถ์ผ์น"
elif [ ! -f .claude/ontology/index.json ]; then
echo "Ontology: SKIPPED (.claude/ontology/index.json not present)"
else
echo "Ontology: SKIPPED (validator not installed in this repo)"
fi
์คํจ ์ /ontology-sync --check๋ฅผ ์คํํ๊ณ ๋ถ์ผ์น๋ฅผ ๋ณด๊ณ ํ๋ค. (scripts/ci/validate-ontology.js๋ ECC ๊ฐ๋ฐ ๋ ํฌ์๋ง ์กด์ฌํ ์ ์์ผ๋ฏ๋ก, ํ์ผ์ด ์์ผ๋ฉด ์คํจ๋ก ๊ฐ์ฃผํ์ง ์๋๋ค.)
# Check for secrets
grep -rn "sk-" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
grep -rn "api_key" --include="*.ts" --include="*.js" . 2>/dev/null | head -10
# Check for console.log
grep -rn "console.log" --include="*.ts" --include="*.tsx" src/ 2>/dev/null | head -10
# Show what changed
git diff --stat
git diff HEAD~1 --name-only
Review each changed file for:
After running all phases, produce a verification report:
VERIFICATION REPORT
==================
Build: [PASS/FAIL]
Types: [PASS/FAIL] (X errors)
Lint: [PASS/FAIL] (X warnings)
Tests: [PASS/FAIL] (X/Y passed, Z% coverage)
Ontology: [PASS/FAIL/SKIPPED]
Security: [PASS/FAIL] (X issues)
Diff: [X files changed]
Overall: [READY/NOT READY] for PR
Issues to Fix:
1. ...
2. ...
For long sessions, run verification every 15 minutes or after major changes:
Set a mental checkpoint:
- After completing each function
- After finishing a component
- Before moving to next task
Run: /verify
This skill complements PostToolUse hooks but provides deeper verification. Hooks catch issues immediately; this skill provides comprehensive review.