Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/daffy0208/ai-dev-standards/validategit clone --depth 1 https://github.com/daffy0208/ai-dev-standardsWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00000 | $0.24307 |
| Opus 5 | $0.00000 | $0.12153 |
| Sonnet 5 | $0.00000 | $0.04861 |
| Haiku 4.5 | $0.00000 | $0.02431 |
Grade C, and why
validate scanned grade C with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
rm -rf dist/ build/ .cache/ node_modules/.cache/ How it starts
The opening of the file, as written. The whole thing — 3,020 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Ultimate Validation Command
Run comprehensive validation of the entire ai-dev-standards codebase. This command validates code quality, runs all tests, and performs end-to-end testing that ensures the application works exactly as a user would experience it.
Initialization
# Start timing for comprehensive validation report
VALIDATION_START_TIME=$(date +%s)
echo ""
echo "🚀 Starting Comprehensive Validation Process..."
echo "⏱️ Start Time: $(date '+%Y-%m-%d %H:%M:%S')"
echo ""
# Check for continue-on-failure mode (for testing Wave 2 features)
if [ "$VALIDATION_CONTINUE_ON_FAILURE" = "true" ]; then
echo "⚠️ VALIDATION_CONTINUE_ON_FAILURE=true detected"
echo " Running in TEST MODE - will continue past failures"
echo " This mode is for verifying Wave 2 features only"
echo " Production validation requires all phases to pass"
echo ""
fi
Helper Functions - Self-Correction Mechanisms
These helper functions provide automatic retry logic, error categorization, and auto-healing capabilities to make validation robust against transient failures.
###############################################################################
# retry_with_backoff: Retry a command with exponential backoff
# Usage: retry_with_backoff <max_attempts> <command>
# Example: retry_with_backoff 3 "npm install"
###############################################################################
retry_with_backoff() {
local max_attempts=$1
shift
local command="$@"
local attempt=1
local timeout=2
local exit_code=0
while [ $attempt -le $max_attempts ]; do
echo " Attempt $attempt/$max_attempts: Running command..."
# Execute command and capture exit code
eval "$command"
exit_code=$?
# Success - return immediately
if [ $exit_code -eq 0 ]; then
if [ $attempt -gt 1 ]; then
echo " ✅ Command succeeded on attempt $attempt"
fi
return 0
fi
# Failed - check if we should retry
if [ $attempt -lt $max_attempts ]; then
echo " ⚠️ Attempt $attempt failed (exit code: $exit_code), retrying in ${timeout}s..."
sleep $timeout
timeout=$((timeout * 2)) # Exponential backoff: 2s, 4s, 8s
fi
attempt=$((attempt + 1))
done
# All attempts failed
echo " ❌ Command failed after $max_attempts attempts (exit code: $exit_code)"
return $exit_code
}
###############################################################################
# categorize_error: Determine if an error is fatal or recoverable
# Usage: categorize_error <exit_code> <error_output>
# Returns: "FATAL" or "RECOVERABLE"
###############################################################################
categorize_error() {
local exit_code=$1
local error_output="$2"
# Fatal error patterns
if echo "$error_output" | grep -qi "ENOSPC\|disk.*full\|no space"; then
echo "FATAL: Disk space exhausted"
return 1
fi
if echo "$error_output" | grep -qi "EACCES\|permission denied"; then
echo "FATAL: Permission denied"
return 1
fi
if echo "$error_output" | grep -qi "MODULE_NOT_FOUND\|Cannot find module"; then
echo "RECOVERABLE: Missing dependencies (run npm install)"
return 0
fi
if echo "$error_output" | grep -qi "ECONNREFUSED\|ETIMEDOUT\|network"; then
echo "RECOVERABLE: Network connectivity issue"
return 0
fi
if echo "$error_output" | grep -qi "rate limit\|429"; then
echo "RECOVERABLE: API rate limit (retry with backoff)"
return 0
fi
# Default categorization based on exit code
if [ $exit_code -eq 1 ]; then
echo "RECOVERABLE: Generic failure (exit code 1)"
return 0
elif [ $exit_code -ge 128 ]; then
echo "FATAL: Signal termination (exit code $exit_code)"
return 1
else
echo "RECOVERABLE: Unknown error (exit code $exit_code)"
return 0
fi
}
###############################################################################
# auto_heal: Attempt automatic fixes for common failures
# Usage: auto_heal <error_type> <context>
# Returns: 0 if healing attempted, 1 if no healing available
###############################################################################
auto_heal() {
local error_type="$1"
local context="$2"
case "$error_type" in
"missing_dependencies")
echo " 🔧 Auto-healing: Installing dependencies..."
npm install > /dev/null 2>&1
if [ $? -eq 0 ]; then
echo " ✅ Dependencies installed successfully"
return 0
else
echo " ❌ Failed to install dependencies"
return 1
fi
;;
"stale_build")
echo " 🔧 Auto-healing: Cleaning and rebuilding..."
rm -rf dist/ build/ .cache/ node_modules/.cache/
npm run build > /dev/null 2>&1
if [ $? -eq 0 ]; then
echo " ✅ Clean rebuild successful"
return 0
else
echo " ❌ Rebuild failed"
return 1
fi
;;
"docker_network")
echo " 🔧 Auto-healing: Recreating Docker network..."
docker network prune -f > /dev/null 2>&1
sleep 2
echo " ✅ Docker network cleaned"
return 0
;;
"github_api_rate_limit")
echo " 🔧 Auto-healing: Waiting for GitHub API rate limit reset..."
RESET_TIME=$(gh api rate_limit --jq '.rate.reset' 2>/dev/null)
if [ ! -z "$RESET_TIME" ]; then
CURRENT_TIME=$(date +%s)
WAIT_TIME=$((RESET_TIME - CURRENT_TIME + 10))
if [ $WAIT_TIME -gt 0 ] && [ $WAIT_TIME -lt 300 ]; then
echo " ⏳ Waiting ${WAIT_TIME}s for rate limit reset..."
sleep $WAIT_TIME
echo " ✅ Rate limit should be reset now"
return 0
fi
fi
echo " ⚠️ Unable to determine rate limit reset time"
return 1
;;
"port_conflict")
echo " 🔧 Auto-healing: Killing processes on conflicting ports..."
# Common test ports: 3000, 5173, 8080
lsof -ti:3000,5173,8080 | xargs kill -9 2>/dev/null
sleep 1
echo " ✅ Port conflicts cleared"
return 0
;;
*)
echo " ℹ️ No auto-healing available for: $error_type"
return 1
;;
esac
}
###############################################################################
# validate_prerequisites: Check and auto-heal missing prerequisites
###############################################################################
validate_prerequisites() {
echo "🔍 Validating prerequisites..."
local missing_prereqs=0
# Check Node.js
if ! command -v node &> /dev/null; then
echo " ❌ Node.js not installed"
missing_prereqs=$((missing_prereqs + 1))
else
echo " ✅ Node.js installed: $(node --version)"
fi
# Check npm
if ! command -v npm &> /dev/null; then
echo " ❌ npm not installed"
missing_prereqs=$((missing_prereqs + 1))
else
echo " ✅ npm installed: $(npm --version)"
fi
# Check dependencies
if [ ! -d "node_modules" ]; then
echo " ⚠️ node_modules missing - attempting auto-heal..."
auto_heal "missing_dependencies" ""
if [ $? -ne 0 ]; then
missing_prereqs=$((missing_prereqs + 1))
fi
else
echo " ✅ Dependencies installed"
fi
# Check jq (required for JSON operations)
if ! command -v jq &> /dev/null; then
echo " ⚠️ jq not installed (required for validation)"
echo " Install with: brew install jq (Mac) or apt install jq (Linux)"
missing_prereqs=$((missing_prereqs + 1))
else
echo " ✅ jq installed"
fi
echo ""
if [ $missing_prereqs -gt 0 ]; then
echo "❌ $missing_prereqs prerequisite(s) missing or failed to auto-heal"
echo " Please install missing prerequisites and try again"
return 1
fi
echo "✅ All prerequisites validated"
echo ""
return 0
}
# Run prerequisite validation before starting phases
validate_prerequisites
if [ $? -ne 0 ]; then
exit 1
fi
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 3,020 lines · 0 tokens per session scan C 423befa59446
validate is a command published in the GitHub repository daffy0208/ai-dev-standards (36 stars, last pushed 8mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 24,307 tokens. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other commands, from other repositories
e2e
使用 Playwright 对 Web UI 进行端到端测试(支持视频录制、Trace 录制、控制台/网络日志捕获).
verify
Grade work that already exists and decide whether it can merge. Runs the project's current unit, integration, and E2E suites plus security scanning and type checking, scores every dimension 0-10, and returns a merge verdict with a VERIFIED-vs-CLAIMED evidence manifest. Writes no test files and edits no source. Use…
debug-playwright
Use this command to debug failing Playwright tests in a source-first, evidence-first workflow.
run-all-tests-and-fix
Execute the full test suite and systematically fix any failures, ensuring code quality and functionality. All test-related commands must pass before completion.
webapp-testing
Toolkit for interacting with and testing local web applications using Playwright. Supports verifying frontend functionality, debugging UI behavior, capturing browser screenshots, and viewing browser logs.
fd-verify
Verify the implementation — run tests, check regression on affect.md files, review and scan; blocks /fd-done on failure.