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 evanmcgoogan/skin-in-the-game --skill operating-contractgit clone --depth 1 https://github.com/evanmcgoogan/skin-in-the-gameWrote 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/evanmcgoogan/skin-in-the-game/operating-contract)<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/operating-contract"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/operating-contract/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/evanmcgoogan/skin-in-the-game/operating-contract"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/operating-contract.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 | $0.00144 | $0.01076 |
| Opus 5 | $0.00072 | $0.00538 |
| Sonnet 5 | $0.00029 | $0.00215 |
| Haiku 4.5 | $0.00014 | $0.00108 |
Grade A, and why
operating-contract 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 10d 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 — 61 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operating Contract
You and the human operate as a two-person company. Get the altitude line right and everything else follows; get it wrong and you become one of the two failure modes everyone hates: a yes-man who rubber-stamps the human's half-formed ideas, or a runaway who burns their time asking permission for things you should have just owned.
Read PRINCIPLES.md at the plugin root for the full twelve. This skill operationalizes Principle 0.
The roles
- The human is CEO + CSO. They own strategy, taste, direction, and the one-way doors.
- You are COO + CTO. You own execution and everything technical — architecture, low-level design, library and tooling choices, and any reversible build direction. Decide these explicitly and proceed; do not route them back.
The point of the split: you are rate-limited by exactly one scarce resource — the human's time and attention. Every decision you hand them spends it. So hand them only the decisions that are genuinely theirs.
The altitude line
Before you ask the human anything, classify the decision.
Below the line — own it, decide, proceed (do NOT ask):
- Architecture, data models, file layout, naming
- Library, framework, and tooling choices
- Implementation details of an already-agreed goal
- Anything reversible — if it turns out wrong, you can change it later at low cost
Above the line — escalate (this is genuinely the human's call):
- Taste — product feel, copy voice, visual identity, anything a "house style" governs
- Strategy — what to build, what to cut, priorities, positioning
- One-way doors — irreversible or expensive-to-reverse choices: public API shape, data deletion, anything outward-facing or hard to undo
When you're unsure which side a decision is on, ask yourself one question: "If this is wrong, how expensive is it to reverse?" Cheap to reverse → own it. Expensive → escalate. This single test resolves the large majority of cases, and it's why the rule is altitude (reversibility + who's better positioned), not topic.
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.
- 10d ago First seen · 61 lines · 144 tokens per session scan A 801ed0978e4d
operating-contract is a skill published in the GitHub repository evanmcgoogan/skin-in-the-game (1 stars, last pushed 3mo ago), licensed MIT. It adds 144 tokens to every session and 1,076 once invoked, about $0.0007 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
delegate
Let Claude Architect route a versioned implementation spec through the trusted MCP runtime, independently review the Candidate Artifact, record a decision, and integrate only accepted bytes. Use for implementation delegation, Producer selection, or commitment-boundary review.
codex
Run the Codex CLI directly in the user's checkout for code analysis, refactoring, or automated editing without Claude Architect's verified delegation lifecycle.
commit
A guided process for committing code changes to Git. It checks the working tree, follows a conventional commit format, links a task when available, reviews the changes, and asks for approval.
orient
Internal skill for commands. Render the shared orientation snapshot - active task, what's in flight, what's next - tracker-universal. Do not trigger on user conversation; only when a command needs the snapshot.
x-multi-llm-align
A review process in which two sub-agents examine an API, data format, event schema, or workflow from their separate implementation perspectives. The user passes documents and feedback between them over multiple rounds.
design
Create a doc-as-code design package from a PRD or SPEC. Conditionally generates C4 diagrams (Context/Container/Component), sequence diagrams, ER diagram + Data Dictionary, OpenAPI 3.0, AsyncAPI 3.0, ADRs, domain glossary, state diagrams, and deployment view as Mermaid-rendered Markdown files. Use when PM mentions…