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.
git clone --depth 1 https://github.com/avelikiy/great_ctoWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/avelikiy/great_cto/sec)<a href="https://agentmods.dev/commands/avelikiy/great_cto/sec"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/sec/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/avelikiy/great_cto/sec"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/sec.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What 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 5.1 | $0.00032 | $0.04139 |
| Opus 5.5 | $0.00013 | $0.01656 |
| Sonnet 5.5 | $0.00006 | $0.00828 |
| Haiku 4.5 | $0.00003 | $0.00414 |
Grade A, and why
sec scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 339 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great_cto security umbrella. This is the single entry point for all security workflows — metrics, threat modeling, SBOM generation, incident response.
Dispatcher
SUBCMD="${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:
status(or no args) → continue below (Steps 1-8 of metrics).threat→ readskills/great_cto/playbooks/threat-model.mdand follow its instructions end-to-end. Pass the remaining args ($1 = arch-slug).sbom→ readskills/great_cto/playbooks/sbom.mdand follow it. $1 = version (optional).incident→ readskills/great_cto/playbooks/security-incident.mdand follow it. $1 = description.rotate→ jump directly to Step 5 below (secret rotation only), skip other metrics.
For threat, sbom, incident: the playbook files are the old /threat-model, /sbom, /security-incident commands — same content, now accessed via /sec <sub>. Read the file, then execute exactly as if it were the top-level command.
status subcommand — Security metrics aggregator
Compute the five security-posture metrics from artefacts produced by security-officer, architect, devops, and /audit. No external scanners, no new telemetry — only what already lives in the repo.
See skills/great_cto/references/sec-metrics.md for formula definitions and data-source documentation.
Setup
source .great_cto/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$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}
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.
- 1mo ago First seen · 339 lines · 32 tokens per session scan A e8199431dcb7
sec is a command published in the GitHub repository avelikiy/great_cto (113 stars, last pushed yesterday), licensed MIT. It adds 32 tokens to every session and 4,139 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
fec-review
Conduct a standardized review of the frontend changes, specified files/directories, or the whole project, output a graded review report and save it as a Markdown file.
develop
Implement skill development issues with TDD-governed workflow.
rust-critique
Deep code critique — read the target Rust code and apply the full review process. Evaluates soundness, ownership, error handling, type design, async correctness, performance, and architecture. Think like a senior Rust engineer giving honest feedback.
review-pr
Review a PR (GitHub or Bitbucket) — single reviewer by default, or a 3-panelist council with --council.
esp-harden
Harden and inspect ESP32 firmware for field failures, crashes, memory, and security.