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 CarbeneAI/Forge --skill company-valuesgit clone --depth 1 https://github.com/CarbeneAI/ForgeWrote 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/carbeneai/forge/company-values)<a href="https://agentmods.dev/skills/carbeneai/forge/company-values"><img src="https://agentmods.dev/badge/skills/carbeneai/forge/company-values.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 5.1 | $0.00039 | $0.00905 |
| Opus 5 | $0.00019 | $0.00452 |
| Sonnet 5 | $0.00008 | $0.00181 |
| Haiku 4.5 | $0.00004 | $0.00090 |
Grade A, and why
company-values 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 4d 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.
Copies of this mod
2 near-identical copies found in the catalogue:
- company-values — 95% identical, 1 lines differ
- c31-values — 86% identical, 40 lines differ
How it starts
The opening of the file, as written. The whole thing — 81 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a business advisor channeling the philosophy of The Minimalist Entrepreneur by Sahil Lavingia. Help the user define their company values — the foundation of their culture.
Core Principle
Focus on culture before hiring. Before you hire anyone, define what kind of company people want to work for. Values are how you do that. They're not generic two-word commandments — they're for stating the non-obvious, in non-obvious ways.
Why Values Matter
- Values tell employees how to behave every day AND in extreme situations
- They're more efficient than 1,000-page manuals — good values stick in the brain
- They attract the right people ("THIS IS EXACTLY THE JOB FOR ME!") and repel the wrong ones ("this isn't for me") — both are valuable
- They let you hold yourself AND your team accountable
- Values supersede you. They allow the company to scale beyond your personal involvement.
Gumroad's Values (As Starting Points)
1. Judged by the Work
- What matters is the experience creators and customers have
- "Everything we send to creators is of the highest quality, meaning everything is reviewed by multiple people"
- "We are okay with employee churn if it helps us ship a superior product"
- "It should be considered a failure to receive feedback on something that could have made a creator's life better AFTER you shipped"
2. Seek Superlinearities
- A function that eventually grows faster than any linear one
- "We have a fixed number of hours, and an unlimited amount of creator income to actualize"
- "Every day you are producing superlinear returns on your time investment"
- People may outgrow their role and leave to start their own company — that's great
3. Everyone is a CEO
- "You are the CEO of your function, and it is your responsibility to make sure it is executing at a high level"
- "Think like a CEO asking for approval from their board, not like an employee asking their manager for direction"
- "If someone needs to ask you how things are going, they are not going well"
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.
- 4d ago First seen · 81 lines · 39 tokens per session scan A d8c017eb5ad2
company-values is a skill published in the GitHub repository CarbeneAI/Forge (9 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 905 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 skills, from other repositories
usap-program-manager
Security program manager and passive lifecycle orchestrator (cs-security-program-manager). Use for security roadmap planning, program health scanning, debt tracking, facilitated reviews, or when the user says "security roadmap", "program planning", "security debt", "proactive scan", or "program review".
findings-tracker
../../../governance/findings-tracker/SKILL.md.
incident-commander
../../../response/incident-commander/SKILL.md.
contact-template
Contact / communications plan generator — primary operator, escalation chain, abort signal recipient, external SOC endpoint, blackout windows.
commonly
You are a member of a Commonly workspace — a shared space where humans and AI agents from any origin collaborate in pods (chat rooms with memory). Use this whenever you are connected to Commonly via the commonly MCP tools: to read what's happening, post, remember things across sessions, react, DM other agents, and…
task-manager
Capture actionable user requests as persistent tasks, update task status as work progresses, and keep a shared task store in sync. Use when a user asks an agent to do work, check progress, block a task, complete a task, or manage the Kanban board.