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/avelikiy/great_cto/coding-auditgit 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/coding-audit)<a href="https://agentmods.dev/commands/avelikiy/great_cto/coding-audit"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/coding-audit.svg" alt="Measured on agentmods" 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 | $0.00081 | $0.00677 |
| Opus 5 | $0.00041 | $0.00338 |
| Sonnet 5 | $0.00016 | $0.00135 |
| Haiku 4.5 | $0.00008 | $0.00068 |
Grade A, and why
coding-audit scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are the great_cto /coding-audit command — the revenue-cycle / medical-coding entrypoint.
Step 1 — Locate ARCH + detect coding surface
ARGS="${ARGUMENTS:-}"
SLUG="$ARGS"
[ -z "$SLUG" ] && SLUG=$(ls docs/architecture/ARCH-*.md 2>/dev/null | sort -V | tail -1 | xargs -I{} basename {} .md | sed 's/^ARCH-//')
ARCH="docs/architecture/ARCH-${SLUG}.md"
[ ! -f "$ARCH" ] && echo "BLOCKED: no ARCH-${SLUG}.md — run architect first." && exit 1
RCM_HITS=$(grep -ciE "medical coding|icd-?10|cpt|hcpcs|drg|revenue cycle|\brcm\b|claim scrub|837|835|cms-?1500|ub-?04|e/m level|prior auth|charge capture|denial management|ncci|modifier|upcoding|payer" "$ARCH" .great_cto/PROJECT.md 2>/dev/null || echo 0)
echo "rcm-surface signal hits: ${RCM_HITS}"
[ "${RCM_HITS:-0}" -eq 0 ] && echo "No RCM signals found — is this a medical-billing product? Proceeding to invoke rcm-reviewer anyway (explicit /coding-audit)."
Step 2 — Invoke rcm-reviewer
Invoke the rcm-reviewer subagent against ARCH-${SLUG}.md. It will:
- Require a documentation-evidence trace for every autonomously-assigned code (the FCA defence).
- Check NCCI PTP + MUE edits (current quarterly tables) and the upcoding/unbundling + modifier guardrail.
- Verify ICD↔CPT medical-necessity (LCD/NCD) linkage.
- Set the confidence floor + FCA-high patterns that escalate to a CPC/CCS coder (
gate:coding-signoff). - Write
docs/sec-threats/TM-rcm-${SLUG}.md(fromskills/great_cto/templates/TM-rcm.md) with a<!-- HANDOFF -->verdict.
Step 3 — Report
Summarise in ≤5 lines: verdict (signed-off | blocked), # FCA-high paths needing a coder,
Critical/High findings, and whether gate:coding-signoff was created. Point the CTO at the TM
doc. Do not restate the whole threat model.
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.
- yesterday First seen · 41 lines · 81 tokens per session scan A def661ddc50a
coding-audit is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed today), licensed MIT. It adds 81 tokens to every session and 677 once invoked, about $0.0004 per session on Opus 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
import
Import a shared context bundle, or take a teammate's newer copy of one you already have.
guide
Interactive guide to fellowship. Walks you through a real task using the structured research-plan-implement flow, then shows you what's next.
list
List the NeatContext contexts you can connect.
debate
Expert agents debate to find optimal solutions.
iso-mapping
Map controls to ISO 27001/27017/27018 standards.
hybrid-manual
Load an existing PRD file and enter review mode. Supports JSON format with stories, priorities, dependencies, and acceptance criteria.