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/spec)<a href="https://agentmods.dev/commands/avelikiy/great_cto/spec"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/spec/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/spec"><img src="https://agentmods.dev/badge/commands/avelikiy/great_cto/spec.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 | $0.00071 | $0.05031 |
| Opus 5.5 | $0.00028 | $0.02012 |
| Sonnet 5.5 | $0.00014 | $0.01006 |
| Haiku 4.5 | $0.00007 | $0.00503 |
Grade A, and why
spec 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 26d 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 — 652 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the great_cto /spec command — product definition in three stages, run in this order, each optional:
discover (what is worth building: outcome → opportunities → experiments) → prd (what and why: an 8-section PRD) →
build (how, for the coding agents: requirements.md + design.md + tasks.md). Start at whichever stage you already know enough for.
Route by the first word of the argument
| First word | Stage |
|---|---|
discover |
## Stage: discover |
prd |
## Stage: prd |
build |
## Stage: build |
retrofit |
## Stage: build, retrofit mode |
| empty, or anything else | ## Stage: build — the whole argument is the project description (what /spec always did) |
Inside a stage, $ARGUMENTS means the argument with the stage word removed. Run only the chosen stage, then stop — each stage ends by naming the next one.
Stage: discover
You are a senior PM running a structured discovery process. Move from divergent opportunity mapping to focused experiment design.
Pipeline position: /spec discover → /spec prd → /spec build / architect → pm → senior-dev
Invocation
/spec discover improve 7-day retention
/spec discover what should we build next for enterprise customers
/spec discover new product: AI writing assistant for non-native speakers
/spec discover ← asks what you're exploring
Step 1 — Understand discovery context
Ask (one question at a time, max 3):
- Outcome: What metric or outcome are you trying to improve? If they have no metric, ask: "What would need to be true for this effort to be a success?"
- What you know: What customer research, feedback, or data do you already have? (interviews, support tickets, NPS, analytics)
- Decision: What decision will this discovery inform? (build/kill, prioritise, pivot, invest)
Accept context from uploaded files (interview transcripts, analytics exports, NPS data, feature requests).
Step 2 — Define the desired outcome
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.
- 26d ago Changed · +373 lines · +50 tokens per session f4a869ac9c7b
- 1mo ago First seen · 279 lines · 21 tokens per session scan A f138bd3b8628
spec is a command published in the GitHub repository avelikiy/great_cto (105 stars, last pushed today), licensed MIT. It adds 71 tokens to every session and 5,031 once invoked, about $0.0003 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
monitor
Pull review comments from a GitHub PR or GitLab MR and plan/dispatch SWE work to address them.
auto-task
Create an agent team for autonomous workflow: plan (Architect teammate + PM teammate) → develop (Developer teammate + Code-tester teammate + QA-tester teammate + Reviewer teammate) → report (no approval gate).
status
The state of play, computed fresh: branch, dirty files, the active sprint, open work, index freshness.
flow
End-to-end feature/bug/refactor pipeline (plan → start → implement → QA → ship → address → cleanup) with an interactive gate at every phase. Resumable via /orc:resume. --jira links a ticket. Workspace-aware.
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.