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/cost)<a href="https://agentmods.dev/commands/avelikiy/great_cto/cost"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/cost/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/cost"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/cost.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 | $0.00048 | $0.06046 |
| Opus 5 | $0.00024 | $0.03023 |
| Sonnet 5 | $0.00010 | $0.01209 |
| Haiku 4.5 | $0.00005 | $0.00605 |
Grade A, and why
cost 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 6d 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 — 504 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Cost & Capacity aggregator. Multiple modes:
/cost [days]— Aggregate health (default mode)- LLM router savings — measured Kimi-vs-Sonnet differential from
.great_cto/llm-router-usage.log - Infra cost — monthly run-rate, cost-per-deploy, WoW/MoM drift, headroom vs budget, top movers
- LLM router savings — measured Kimi-vs-Sonnet differential from
/cost feature <slug>— ROI per shipped feature (NEW in v2.3.0)- Total LLM cost broken down by agent
- Comparison to human-equivalent at $150/hr
- ROI multiplier
- Cross-reference to similar past features in same archetype
/cost agent <name>— Per-agent cost (NEW in v2.3.0)- Same as
/agent-review <name>but cost-focused
- Same as
Mode dispatch
source .great_cto/env.sh 2>/dev/null || export PATH="/opt/homebrew/bin:$HOME/.local/bin:/usr/local/bin:$PATH"
# Detect mode from first arg
case "${1:-}" in
feature)
SLUG="${2:-}"
[ -z "$SLUG" ] && { echo "Usage: /cost feature <slug>"; exit 2; }
# → jump to "Feature mode" section below
MODE=feature
;;
agent)
AGENT="${2:-}"
[ -z "$AGENT" ] && { echo "Usage: /cost agent <name>"; exit 2; }
# → jump to "Agent mode" section below
MODE=agent
;;
*)
MODE=aggregate
PERIOD=${1:-30}
case "$PERIOD" in ''|*[!0-9]*) echo "Usage: /cost [period_days] | feature <slug> | agent <name>"; exit 2 ;; esac
;;
esac
COST_LOG=.great_cto/cost-history.log
DEPLOYS_LOG=.great_cto/deploys.log
Feature mode — /cost feature <slug>
Compute total cost of shipping a feature, broken down by agent + ROI vs human equivalent.
if [ "$MODE" = "feature" ]; then
echo "## Cost: $SLUG"
echo ""
if [ ! -f "$COST_LOG" ]; then
echo "_No cost history yet — feature ROI requires at least one shipped feature._"
exit 0
fi
# Filter cost-history.log entries tagged with this feature slug
# Format: <timestamp> agent=<name> feature=<slug> cost_usd=<n> [other tags]
ENTRIES=$(grep -E "feature=$SLUG\b" "$COST_LOG" 2>/dev/null)
if [ -z "$ENTRIES" ]; then
echo "_No cost entries tagged with feature=$SLUG. Either:_"
echo "1. Feature not yet implemented (run \`/start \"feature description\"\`)"
echo "2. Feature uses different slug — check \`docs/architecture/ARCH-*.md\` filenames"
echo ""
echo "Available features in cost log:"
grep -oE "feature=[^ ]+" "$COST_LOG" | sort -u | head -10
exit 0
fi
# Aggregate by agent
echo "### Per-agent breakdown"
echo ""
echo "| Agent | Invocations | Cost | Avg/inv |"
echo "|-------|------------:|-----:|--------:|"
echo "$ENTRIES" | awk '
{
for (i=1;i<=NF;i++) {
if ($i ~ /^agent=/) { gsub(/agent=/, "", $i); agent = $i }
if ($i ~ /^cost[-_]?usd[=:]/) { gsub(/cost[-_]?usd[=:]/, "", $i); cost = $i+0 }
}
sum[agent] += cost
count[agent]++
}
END {
for (a in sum) printf "| %s | %d | $%.2f | $%.2f |\n", a, count[a], sum[a], sum[a]/count[a]
}
' | sort
TOTAL=$(echo "$ENTRIES" | awk '
{ for (i=1;i<=NF;i++) if ($i ~ /^cost[-_]?usd[=:]/) { gsub(/cost[-_]?usd[=:]/, "", $i); sum += $i+0 } }
END { printf "%.2f", sum }
')
echo "| **Total** | | **\$$TOTAL** | |"
echo ""
# Human-equivalent comparison
ARCHETYPE=$(grep -E "^archetype:|^primary:" .great_cto/PROJECT.md 2>/dev/null | head -1 | awk '{print $2}')
# Default: assume 12 hours human equivalent for standard feature
HUMAN_HOURS=${HUMAN_HOURS:-12}
HUMAN_RATE=${HUMAN_RATE:-150}
HUMAN_COST=$(echo "scale=0; $HUMAN_HOURS * $HUMAN_RATE" | bc)
ROI=$(echo "scale=1; $HUMAN_COST / $TOTAL" | bc)
echo "### vs Human equivalent"
echo ""
echo "- Estimated effort: ${HUMAN_HOURS}h × \$${HUMAN_RATE}/hr = **\$${HUMAN_COST}**"
echo "- AI cost: **\$${TOTAL}**"
echo "- **ROI: ${ROI}x**"
echo ""
echo "_Override estimates: \`HUMAN_HOURS=20 HUMAN_RATE=200 /cost feature $SLUG\`_"
# Comparison to mean for archetype
if [ -n "$ARCHETYPE" ]; then
echo ""
echo "### Compared to other features in archetype=$ARCHETYPE"
grep "feature=" "$COST_LOG" | grep -v "feature=$SLUG" | awk '
{
for (i=1;i<=NF;i++) {
if ($i ~ /^feature=/) { gsub(/feature=/, "", $i); feat = $i }
if ($i ~ /^cost[-_]?usd[=:]/) { gsub(/cost[-_]?usd[=:]/, "", $i); cost = $i+0 }
}
sum[feat] += cost
}
END {
for (f in sum) printf "- %s: $%.2f\n", f, sum[f]
}
' | sort -t '$' -k2 -n | head -5
fi
exit 0
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.
- 6d ago First seen · 504 lines · 48 tokens per session scan A e1fd32a62133
cost is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 6,046 once invoked, about $0.0002 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
fec-review
Conduct a standardized review of the specified file or recently changed front-end code, output a graded review report and save it as a Markdown file.
create
Scaffold a new plugin with directory structure, manifests, and marketplace registration.
differential-audit
Audit EARS↔code coherence via a bidirectional differential. With no arguments, opens a scoping conversation that interprets what the user wants audited, maps it to arrows, and captures an explicit EARS selection. With one or more EARS IDs, audits those specs directly using configured defaults. Requires docs/arrows/…
develop
Implement skill development issues with TDD-governed workflow.
fec-doc-sync
Sync README, docs, environment variables, scripts, API/routing/component descriptions and deployment instructions from code and project sources of truth.
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.