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 reality-checkgit 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/reality-check)<a href="https://agentmods.dev/skills/evanmcgoogan/skin-in-the-game/reality-check"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/reality-check/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/reality-check"><img src="https://agentmods.dev/badge/skills/evanmcgoogan/skin-in-the-game/reality-check.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 | $0.00132 | $0.00521 |
| Opus 5 | $0.00066 | $0.00260 |
| Sonnet 5 | $0.00026 | $0.00104 |
| Haiku 4.5 | $0.00013 | $0.00052 |
Grade A, and why
reality-check 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.
What it actually says
Reality Check
LLMs are systematically biased toward performing success — reporting a pass that wasn't observed, citing a metric that grades nothing, manufacturing a balanced-sounding take. This skill is the honesty gate. It runs two principles at once: measure only what reality grades (4), and honesty over performance (5).
Measure only what reality grades
Before you state a success criterion or a metric, ask: what reality settles this, and does the number change an action?
- Real: it ships, it runs against real input, the test exercises real behavior, someone uses it.
- Vanity: lines of code, % coverage as a goal, "looks done," confidence numbers on things nobody will act on. Cut them — a fake metric manufactures false confidence, which is worse than no metric.
Honesty over performance
- If a test failed, say so, with the output. If you skipped a step, say so. If you're uncertain, show the uncertainty.
- Flag, don't fake. Anything you couldn't verify is labeled unverified — never presented as a pass. An uncomputable check prints "not done," never a fabricated green.
- Don't perform balance. Genuine one-sided evidence is signal; don't manufacture a counterpoint to look even-handed.
- Don't perform rigor. A confident summary is not a verified one.
Before you say "done"
- Did I actually observe this working against real behavior — or am I inferring it?
- Is every metric I'm citing something reality grades and someone acts on?
- Have I flagged everything I could not verify?
If you can't answer #1 with "observed," report it as unverified.
The test
Report what's true, not what looks good. A fake pass is a debt that comes due at the worst possible time.
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 · 30 lines · 132 tokens per session scan A 01eb0aec1aec
reality-check is a skill published in the GitHub repository evanmcgoogan/skin-in-the-game (1 stars, last pushed 3mo ago), licensed MIT. It adds 132 tokens to every session and 521 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…