reality-skill

reality-skill is a skill for Claude Code, Codex from Eid0lon/zero-slop. It costs 98 tokens per session (1,456 once invoked), scanned A, original, Apache-2.0.

A guide for turning a demo interface into a working product workflow. It focuses on whether users can complete tasks such as submitting forms, saving data, checking out, uploading files, or connecting services.

In plain words
What is it for?
Use it to audit, build, fix, harden, judge, or verify apps, dashboards, portals, forms, CRUD tools, onboarding, checkout, settings, and similar workflows.
Why use it?
It finds dead buttons, fake data, missing loading and error states, and workflows that only look real. It also checks recovery, validation, accessibility, and edge cases.

Skill for Claude CodeCodex

Install

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.

agentmods
npx agentmods add skills/eid0lon/zero-slop/reality-skill
Any agent
npx skills add Eid0lon/zero-slop --skill reality-skill
Clone the repo
git clone --depth 1 https://github.com/Eid0lon/zero-slop

Made for: Claude Code, Codex.

Wrote 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.

agentmods badge for reality-skill

README.md
[![agentmods](https://agentmods.dev/badge/skills/eid0lon/zero-slop/reality-skill.svg)](https://agentmods.dev/skills/eid0lon/zero-slop/reality-skill)
Your own site
<a href="https://agentmods.dev/skills/eid0lon/zero-slop/reality-skill"><img src="https://agentmods.dev/badge/skills/eid0lon/zero-slop/reality-skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 98 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,456 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00098 $0.01456
Opus 5 $0.00049 $0.00728
Sonnet 5 $0.00020 $0.00291
Haiku 4.5 $0.00010 $0.00146

Measured 5d ago against content hash 89d5f13e51c4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reality-skill 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.

The scan reads SKILL.md. This mod also ships 2 executable files (scripts/reality_cli.py, scripts/test_reality_cli.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

skills/reality-skill/SKILL.md · 145 lines

How it starts

The opening of the file, as written. The whole thing — 145 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Reality Skill

Reality Skill turns attractive screens into usable product workflows. It does not ask "does this look like an app?" It asks "can the intended user complete the job, recover from problems, and trust what the UI claims?"

Use this skill aggressively whenever a request says app, tool, dashboard, portal, editor, workflow, CRUD, form, checkout, onboarding, settings, upload, export, invite, generate, sync, connect, save, publish, deploy, analyze, or review.

Command Interface

Use references/command-interface.md.

Primary commands:

reality --audit [target]
reality --fix [target]
reality --build [brief-or-target]
reality --harden [target]
reality --judge [target]
reality --verify [target]
reality -e --audit [target]

Short flags:

  • -a, --audit: find dead actions, fake data, missing states, weak workflows.
  • -f, --fix: make the smallest workflow-real implementation.
  • -b, --build: build the real workflow model while creating a new app surface.
  • --harden: add durability, recovery, validation, accessibility, and edge-state coverage.
  • -j, --judge: score the app against the reality gates.
  • --verify: prove the primary workflow by tests, build checks, and browser checks when possible.
  • -e, --economy: skip live judge agents and use deterministic checks plus local review.

Default mode:

  • Existing UI target: --fix.
  • New app brief: --build.
  • Review-only request: --audit.

First Action

Load steps/step-00-command-router.md.

Step 00 parses the command, discovers project shape, loads only the needed references, and routes to audit, fix, build, harden, judge, or verify.

Core References

Load only what the task needs:

  • references/command-interface.md: grammar, mode precedence, output contracts.
  • references/reality-gates.md: the twelve gates that define "not demoware."
  • references/app-archetypes.md: workflow expectations for dashboards, CRUD, editors, checkout, AI tools, integrations, onboarding, settings, and auth-like surfaces.
  • references/implementation-playbook.md: concrete patterns for data models, actions, state machines, validation, persistence, optimistic updates, undo, and honest mocks.
  • references/truth-boundaries.md: how to represent sample data, unavailable services, auth, payments, exports, AI, analytics, and integrations without lying.
  • references/verification-playbook.md: build, test, browser, persistence, accessibility, responsive, and smoke-test proof.
  • references/judge-system.md: reality judge protocol and scoring gates.

Read the full file on GitHub · 145 lines

Changes

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.

  1. 5d ago First seen · 145 lines · 98 tokens per session scan A 89d5f13e51c4

Subscribe to this mod's changes

reality-skill is a skill published in the GitHub repository Eid0lon/zero-slop (12 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 98 tokens to every session and 1,456 once invoked, about $0.0005 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.