aedt-bias-audit
HR-AI / AEDT bias audit. Invokes hr-ai-reviewer to assess NYC LL 144, EEOC, Illinois AIVIA, Colorado SB 205, EU AI Act Annex III applicability and produce…
Security umbrella: posture metrics, threat model, SBOM, incident workflow. Subcommands: status (default) | threat | sbom | incident | rotate.
> /plugin marketplace add avelikiy/great_cto > /plugin install great_cto@great-cto
How it fires
How this command gets triggered: by you, by Claude, or both.
/secContext preview
What this command does when you run it.
Security umbrella: posture metrics, threat model, SBOM, incident workflow. Subcommands: status (default) | threat | sbom | incident | rotate.
description: "Security umbrella: posture metrics, threat model, SBOM, incident workflow. Subcommands: status (default) | threat | sbom | incident | rotate." argument-hint: "[subcommand] [args...] — default: status. Examples: /sec | /sec status 7 | /sec threat stripe-subscriptions | /sec sbom | /sec incident \"creds leaked\"" user-invocable: true allowed-tools: Read, Write, Bash, Glob, Grep model: sonnet
You are the great_cto security umbrella. This is the single entry point for all security workflows — metrics, threat modeling, SBOM generation, incident response.
SUBCMD="${1:-status}"
shift 2>/dev/null || true # remaining args are for subcommand
case "$SUBCMD" in
status|threat|sbom|incident|rotate) ;;
*)
echo "Usage: /sec [subcommand] [args]"
echo ""
echo " status [days] — security posture metrics (default: 30d)"
echo " threat [arch-slug] — STRIDE threat model for a feature"
echo " sbom [version] — generate CycloneDX SBOM for release"
echo " incident \"<desc>\" — security-incident workflow (DORA/GDPR)"
echo " rotate — show overdue secret rotations"
echo ""
echo "Unknown subcommand: $SUBCMD"
exit 2 ;;
esac**Routing:**
**For `threat`, `sbom`, `incident`**: the playbook files are the old `/threat-model`, `/sbom`, `/security-incident` commands — same content, now accessed via `/sec <sub>`. Read the file, then execute exactly as if it were the top-level command.
---
Compute the five security-posture metrics from artefacts produced by `security-officer`, `architect`, `devops`, and `/audit`. No external scanners, no new telemetry — only what already lives in the repo.
See `skills/great_cto/references/sec-metrics.md` for formula definitions and data-source documentation.
source .great_cto/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
# After `shift` above, $1 is now the first arg after the subcommand
PERIOD=${1:-30}
case "$PERIOD" in
''|*[!0-9]*) echo "Usage: /sec status [period_days] (got: $PERIOD)"; exit 2 ;;
esac
NOW_EPOCH=$(date +%s)
WINDOW_START=$(( NOW_EPOCH - PERIOD * 86400 ))
SEC_BASELINE=.great_cto/sec-baseline.log
ARCHETYPE=$(grep "^archetype:" .great_cto/PROJECT.md 2>/dev/null | awk '{print $2}'); ARCHETYPE=${ARCHETYPE:-web-service}Reference: `skills/great_cto/references/security-tiers.md`. Compute effective tier from archetype + signals emitted by `senior-dev`.
case "$ARCHETYPE" in
web3|iot-embedded|regulated) TIER_DEFAULT=deep ;;
ai-system|commerce|infra) TIER_DEFAULT=standard ;;
web-service|mobile-app|data-platform|library) TIER_DEFAULT=baseline ;;
*) TIER_DEFAULT=baseline ;;
esac
TIER_OVERRIDE=$(grep "^default-tier:" .great_cto/PROJECT.md 2>/dev/null | awk '{print $2}')
TIER_EFFECTIVE="${TIER_OVERRIDE:-$TIER_DEFAULT}"
SIGNAL_LOG=.great_cto/security-signals.log
SIGNALS_FIRED=""
if [ -f "$SIGNAL_LOG" ]; then
for S in pci-dep-introduced crypto-dep-introduced auth-path-changed pii-field-added iac-perimeter-changed high-cve-in-dep external-ingest-added; do
if grep -q "SECURITY_SIGNAL: $S " "$SIGNAL_LOG"; then
SIGNALS_FIRED="$SIGNALS_FIRED $S"
case "$TIER_EFFECTIVE" in baseline) TIER_EFFECTIVE=standard ;; esac
fi
done
fi
echo ""
echo "─ Current tier: $TIER_EFFECTIVE (archetype=$ARCHETYPE default=$TIER_DEFAULT${TIER_OVERRIDE:+ override=$TIER_OVERRIDE})"
if [ -n "$SIGNALS_FIRED" ]; then
echo " Signals upgrading tier:"
for S in $SIGNALS_FIRED; do echo " · $S"; done
fi
echo ""iso_to_epoch() {
python3 -c "import sys,datetime; print(int(datetime.datetime.fromisoformat(sys.argv[1].replace('Z','+00:00')).timestamp()))" "$1" 2>/dev/null || echo 0
}Source: `docs/cve-log.md` — lines in format `YYYY-MM-DD | CVE-YYYY-NNNNN | severity | status | resolved:YYYY-MM-DD | note`.
CVE_LOG=docs/cve-log.md
CVE_MTTR_DAYS="-"
CVE_OPEN_CRITICAL=0
CVE_OPEN_OVERDUE_14D=0
if [ -f "$CVE_LOG" ]; then
python3 - "$CVE_LOG" "$NOW_EPOCH" "$WINDOW_START" <<'PY'
import sys, datetime, statistics
path, now, window_start = sys.argv[1], int(sys.argv[2]), int(sys.argv[3])
durations = []
open_critical = 0
open_overdue = 0
with open(path) as f:
for line in f:
line = line.strip()
if not line or line.startswith("#"): continue
parts = [p.strip() for p in line.split("|")]
if len(parts) < 4: continue
try:
advisory = int(datetime.datetime.fromisoformat(parts[0]).timestamp())
except Exception:
continue
severity = parts[2].lower() if len(parts) > 2 else ""
status = parts[3].lower() if len(parts) > 3 else ""
resolved_ts = None
for p in parts[4:]:
if p.startswith("resolved:"):
try:
resolved_ts = int(datetime.datetime.fromisoformat(p.split(":",1)[1]).timestamp())
except Exception: pass
if status == "open":
if severity == "critical":
open_critical += 1
if (now - advisory) / 86400 > 14:
open_overdue += 1
elif resolved_ts and advisory >= window_start - 90*86400:
# include resolved CVEs in a 90-day mYou already have the agent. This is everything around it. great_cto runs Claude Code as a pipeline of 70 specialist agents — an independent model checks each stage before the next builds on it, spending caps refuse rather than warn, and three decisions stay yours: what gets built, how, and whether it ships.
Repo: avelikiy/great_cto
HR-AI / AEDT bias audit. Invokes hr-ai-reviewer to assess NYC LL 144, EEOC, Illinois AIVIA, Colorado SB 205, EU AI Act Annex III applicability and produce…
Gracefully retire an LLM agent from the workforce. Archives prompt, removes from sync list, keeps verdicts for audit. Like firing a human — but reversible.
Performance review for an LLM agent (or all agents). Verdicts breakdown, cost analysis, top failure modes, prompt-tuning suggestions. Like a human '1:1' but…
API platform contract review. Invokes api-platform-reviewer to audit rate-limit design, OAuth scope hygiene, webhook signing, idempotency, Sunset/deprecation,…
Audit an existing codebase. Detects stack, finds gaps, creates tasks, generates PROJECT.md.
Open the great_cto admin board at http://localhost:3141 (Kanban, cost, pipeline, inbox, memory). Starts it in background if not running.