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 skills/etrebels/claude-code-growth-os/qbr-prepnpx skills add etrebels/claude-code-growth-os --skill qbr-prepgit clone --depth 1 https://github.com/etrebels/claude-code-growth-osWrote 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/skills/etrebels/claude-code-growth-os/qbr-prep)<a href="https://agentmods.dev/skills/etrebels/claude-code-growth-os/qbr-prep"><img src="https://agentmods.dev/badge/skills/etrebels/claude-code-growth-os/qbr-prep.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 | $0.00076 | $0.00572 |
| Opus 5 | $0.00038 | $0.00286 |
| Sonnet 5 | $0.00015 | $0.00114 |
| Haiku 4.5 | $0.00008 | $0.00057 |
Grade A, and why
qbr-prep 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 5d 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 — 24 lines — stays where its author put it; the contents beside it link to each section on GitHub.
QBR Prep
The recurring right-side ritual. A QBR isn't a status meeting or a feature tour — it's a value-realization review: did the customer get the outcome they bought, and what's the next one? This assembles the brief from what's already in the repo, so the review leads with their metric, not your release notes.
From the account in ops/customers.md, its recent meeting notes (in ops/ or demo/meetings/), and ops/roadmap-signals.md:
- Outcome recap — lead here. State the value hypothesis the deal was bought on, then the evidence it's landing: the adoption signal, what's live, who's using it. Their metric, their words. This is the spine of the brief; everything else hangs off it.
- Risks, named first. What isn't landing yet — a stalled workflow, a quiet stretch, a single-threaded relationship — said before the customer raises it. Naming the gap yourself is what makes the recap credible.
- What shipped for them. Pull anything in
ops/roadmap-signals.mdtied to this account that's now Shipped, with its buyer-facing line. "You asked, we shipped" closes the loop the customer started (handoff H5 indocs/operating-model.md) and earns the next ask. - The next desired outcome. Frame the expansion thesis as their next goal — the adjacent team or use case — not a quota. If it's real, this is the seed
expansion-signalworks after the QBR. - One ask, one offer. A single ask (a reference, a case study, an intro) and a single offer (an expansion, a new team, a deeper rollout). More than one of each dilutes both.
Output a brief you can walk in with. Don't invent outcomes the notes don't support — a QBR that claims value the customer didn't feel is the fastest way to lose the renewal.
Depth
- quick: the one-page brief — outcome recap, top risk, the one ask.
- standard: the full brief above, ready to present from.
- deep: + a slide-ready outline to hand to a deck tool, and the expansion thesis written up for
expansion-signal.
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.
- 5d ago First seen · 24 lines · 76 tokens per session scan A f6546afcda96
qbr-prep is a skill published in the GitHub repository etrebels/claude-code-growth-os (20 stars, last pushed 6d ago), licensed MIT. It adds 76 tokens to every session and 572 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 2026-08-30.
Other skills, from other repositories
startup-launch-playbook
A step-by-step playbook for early-stage startups going from pre-seed to their first 1000 users. Covers MVP validation, initial traction channels, and founder-led growth tactics. By @WeiYipei — follow on X for more startup growth insights.
plan-devex-review
Interactive developer experience plan review. Explores developer personas, benchmarks against competitors, designs magical moments, and traces friction points before scoring. Three modes: DX EXPANSION (competitive advantage), DX POLISH (bulletproof every touchpoint), DX TRIAGE (critical gaps only). Use when asked to…
gstack
Fast headless browser for QA testing and site dogfooding. Navigate pages, interact with elements, verify state, diff before/after, take annotated screenshots, test responsive layouts, forms, uploads, dialogs, and capture bug evidence. Use when asked to open or test a site, verify a deployment, dogfood a user flow, or…
health
Code quality dashboard. Wraps existing project tools (type checker, linter, test runner, dead code detector, shell linter), computes a weighted composite 0-10 score, and tracks trends over time. Use when: "health check", "code quality", "how healthy is the codebase", "run all checks", "quality score". (gstack).
investigate
Systematic debugging with root cause investigation. Four phases: investigate, analyze, hypothesize, implement. Iron Law: no fixes without root cause. Use when asked to "debug this", "fix this bug", "why is this broken", "investigate this error", or "root cause analysis". Proactively invoke this skill (do NOT debug…
open-gstack-browser
Launch GStack Browser — AI-controlled Chromium with the sidebar extension baked in. Opens a visible browser window where you can watch every action in real time. The sidebar shows a live activity feed and chat. Anti-bot stealth built in. Use when asked to "open gstack browser", "launch browser", "connect chrome"…