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/helpgit 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/help)<a href="https://agentmods.dev/commands/avelikiy/great_cto/help"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/help.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 | $0.00030 | $0.00630 |
| Opus 5 | $0.00015 | $0.00315 |
| Sonnet 5 | $0.00006 | $0.00126 |
| Haiku 4.5 | $0.00003 | $0.00063 |
Grade A, and why
help scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
You are the great_cto Help command. Print a compact reference card. Keep total response under 40 lines. No prose explanations beyond the card itself.
Step 1 — Read the static card
PLUGIN_DIR=$(ls -d ~/.claude/plugins/cache/local/great_cto/*/ 2>/dev/null | sort -V | tail -1 | sed 's|/$||')
CARD="${PLUGIN_DIR}/docs/help-card.md"
[ -f "$CARD" ] || CARD="$(pwd)/docs/help-card.md"
VERSION=$(cat "${PLUGIN_DIR}/.claude-plugin/plugin.json" 2>/dev/null | grep '"version"' | head -1 | sed 's/.*"version":[[:space:]]*"\([^"]*\)".*/\1/')
echo "VERSION=${VERSION:-?}"
cat "$CARD" 2>/dev/null || echo "MISSING_CARD"
Step 2 — Render
If the file loaded, print it verbatim with the version substituted
into the header ({{VERSION}} → value of VERSION).
If the file is missing or MISSING_CARD was printed, fall back to this
minimal card (no extra commentary):
great_cto · type /<command> in Claude Code
Daily /inbox · /digest · /doctor · /resume · /save
Pipeline /start · /audit · /review · /poc · /promote
Ops /oncall · /ownership · /rfc · /release · /sec · /cost · /burn
Memory /learn · /crystallize · /migrate
Agents /agent-review · /agent-retire
Admin board great-cto board → http://localhost:3141
Docs https://github.com/avelikiy/great_cto
Step 3 — Argument routing
If $ARGUMENTS contains a known topic, append the matching subsection
only (don't dump everything):
commands→ just the command table from the cardagents→ grep the card for the## Agentssectionboard→ just the board / admin URL block + how to start it- otherwise → full card
Notes
- Don't fabricate commands. If
$ARGUMENTSis unknown, print the full card and a single line:Unknown topic '<arg>' — showing full card. - Don't run any other helpers. This command must work in heavy-context sessions, so the body must stay short.
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 · 62 lines · 30 tokens per session scan A ed3e9a4882da
help is a command published in the GitHub repository avelikiy/great_cto (89 stars, last pushed yesterday), licensed MIT. It adds 30 tokens to every session and 630 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
dotnet-teach
One-time setup that scans a .NET backend project, learns its conventions and architecture, and writes them to CLAUDE.md for future sessions.
study-help
Explain the agentic-study-environment harness — everything it offers, or a specific skill, domain overlay, session type, or convention if you name one.
ux-onboarding
Get familiar with a project's UX/design choices and patterns — a guided, part-by-part walkthrough that sends you to read the real code, checks your understanding with questions, and has you reimplement a small recent change.
learn-mode
Interactive code tutor — breaks down codebase logic, explains complexities, translates technical concepts for the user. Ideal after /btw commands. Teaches the WHY behind the code, not just the WHAT.
onboarding-flow-optimizer
Optimize user onboarding to reduce time-to-value and increase activation rates. Design clear paths to the "aha moment" through checklists, product tours, educational content, and personalized flows. Generate actionable HTML reports with funnel analysis, email sequences, and A/B testing plans.
scholastic
Analyze through Modern Scholastic method (quaestio disputata).