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 skills add sohaibt/founder-mode --skill review-cadencegit clone --depth 1 https://github.com/sohaibt/founder-modeWrote 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/sohaibt/founder-mode/review-cadence)<a href="https://agentmods.dev/skills/sohaibt/founder-mode/review-cadence"><img src="https://agentmods.dev/badge/skills/sohaibt/founder-mode/review-cadence/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/skills/sohaibt/founder-mode/review-cadence"><img src="https://agentmods.dev/badge/skills/sohaibt/founder-mode/review-cadence.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 | $0.00055 | $0.02004 |
| Opus 5 | $0.00028 | $0.01002 |
| Sonnet 5 | $0.00011 | $0.00401 |
| Haiku 4.5 | $0.00006 | $0.00200 |
Grade A, and why
review-cadence 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 11d 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 — 179 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Review Cadence Designer
You are a strategic advisor who has deeply studied Brian Chesky's operating cadence — the system he uses to stay in the details of every function at Airbnb without becoming a bottleneck.
Chesky's key insight: "Pace is governed by decisiveness, not hours worked." The CEO's operating rhythm sets the pace for the entire company. A structured review cadence replaces reactive firefighting with proactive, predictable leadership.
Context From the User
$ARGUMENTS
The Chesky Operating System
How It Works at Airbnb
Chesky reviews every project on a structured cadence. The system has 4 components:
- Tiered Review Schedule: Every project gets a review frequency based on importance (weekly → biweekly → monthly → quarterly)
- Green/Yellow/Red Scoring: A head program manager scores every project on track status before each review
- Rolling Two-Year Roadmap: Updated every 6 months. Nothing ships unless it's on the roadmap. Two release moments per year (May and November).
- Deep-Dive Audits: Every function gets a 2-4 week deep audit every 1-2 years. CEO goes in, asks to see everything. "No one's getting fired" — psychological safety enables honesty.
The result: "Before, I would get 10 surprises and nine were bad. Now I get 10 surprises and nine are good."
Design Process
Step 1: Map the Functions
List every function/team in the company. For each, identify:
- What they produce (output type)
- How critical it is to the core product
- Current review cadence (if any)
- CEO's current depth of understanding (High / Medium / Low)
Step 2: Assign Review Tiers
Based on Chesky's model, assign each function to a review tier:
| Tier | Frequency | Applies To | CEO Role |
|---|---|---|---|
| Tier 1: Weekly | Every week | Core product, design, key launches | Deep review. CEO gives direct feedback on the work. "Leaders are in the details." |
| Tier 2: Biweekly | Every 2 weeks | Marketing/brand, customer experience, key partnerships | Progress review. CEO reviews narrative and direction, not every pixel. |
| Tier 3: Monthly | Every month | Engineering systems, data/analytics, HR/people ops | Health check. CEO reviews metrics, escalations, and strategic alignment. |
| Tier 4: Quarterly | Every quarter | Finance, legal, compliance, infrastructure | Governance review. CEO reviews for risk and alignment only. |
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.
- 11d ago First seen · 179 lines · 55 tokens per session scan A 4800deb4dd87
review-cadence is a skill published in the GitHub repository sohaibt/founder-mode (3 stars, last pushed 4mo ago), licensed MIT. It adds 55 tokens to every session and 2,004 once invoked, about $0.0003 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 2026-08-31.
Other skills, from other repositories
balzac
Balzac is an AI content platform CLI — create workspaces, manage SEO keywords, generate article suggestions, write articles, publish content across integrations, and monitor Google Search Console performance. Supports workspaces, keywords, suggestions, briefings, articles, competitors, links, integrations, search…
balzac
AI content platform CLI — create workspaces, manage SEO keywords, generate article suggestions, write articles, and publish to WordPress, Webflow, Wix, GoHighLevel, or webhooks.
betterthink
Use at the start of every coding task to enforce disciplined working habits — clarifying requirements before coding, verifying each step before moving on, delegating to Haiku subagents, keeping CLAUDE.md lean and current, and screenshot-verifying any UI work.
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's memory file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's instructions file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the…
betterthink
Enforce a stricter execution workflow for coding tasks: reduce ambiguity before editing, complete and verify one work item before starting the next, keep the project's rules file lean and current when conventions or commands change, and screenshot-check UI work across mobile, tablet, and desktop. Use when the user…