reality

A codebase scan that checks the actual project structure and implementation against its documented architecture.

In plain words
What is it for?
It helps identify the project type, inspect its size and structure, check tests and documentation, and produce either a quick health report or a deeper analysis.
Why use it?
It helps reveal architecture problems, missing tests, documentation drift, oversized files, and unfinished work that may be hidden by the project documentation.

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/fall-out-bug/sdp/reality
Any agent
npx skills add fall-out-bug/sdp --skill reality
Clone the repo
git clone --depth 1 https://github.com/fall-out-bug/sdp

Made for: Claude Code, Codex.

Per session 15 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,150 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 $0.00015 $0.01150
Opus 5 $0.00008 $0.00575
Sonnet 5 $0.00003 $0.00230
Haiku 4.5 $0.00002 $0.00115

Measured 2d ago against content hash 23d58047c382, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

reality 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 2d 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.

prompts/skills/reality/SKILL.md · 160 lines

How it starts

The opening of the file, as written. The whole thing — 160 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@reality - Codebase Analysis & Architecture Validation

Analyze what's actually in your codebase (vs. what's documented).


Workflow

When user invokes @reality:

  1. Auto-detect project type
  2. Run scan based on mode (--quick, --deep, --focus)
  3. Spawn expert agents in parallel using Task tool
  4. Synthesize report with health score

Step 0: Auto-Detect Project Type

# Detect language/framework
if [ -f "go.mod" ]; then PROJECT_TYPE="go"
elif [ -f "pyproject.toml" ] || [ -f "requirements.txt" ]; then PROJECT_TYPE="python"
elif [ -f "pom.xml" ] || [ -f "build.gradle" ]; then PROJECT_TYPE="java"
elif [ -f "package.json" ]; then PROJECT_TYPE="nodejs"
else PROJECT_TYPE="unknown"
fi

Step 1: Quick Scan (--quick mode)

Analysis:

  1. Project size (lines of code, file count)
  2. Architecture (layer violations, circular dependencies)
  3. Test coverage (if tests exist, estimate %)
  4. Documentation (doc coverage, drift detection)
  5. Quick smell check (TODO/FIXME/HACK comments, long files)

Output: Health Score X/100 + Top 5 Issues

Step 2: Deep Analysis (--deep mode)

Spawn 8 parallel expert analyses using Task tool with subagent_type:

Task(subagent_type="general-purpose", prompt="Analyze ARCHITECTURE...")
Task(subagent_type="general-purpose", prompt="Analyze CODE QUALITY...")
Task(subagent_type="general-purpose", prompt="Analyze TESTING...")
Task(subagent_type="general-purpose", prompt="Analyze SECURITY...")
Task(subagent_type="general-purpose", prompt="Analyze PERFORMANCE...")
Task(subagent_type="general-purpose", prompt="Analyze DOCUMENTATION...")
Task(subagent_type="general-purpose", prompt="Analyze TECHNICAL DEBT...")
Task(subagent_type="general-purpose", prompt="Analyze STANDARDS...")

Expert agents:

  1. ARCHITECTURE expert - Layer mapping, dependencies, violations
  2. CODE QUALITY expert - File size, complexity, duplication
  3. TESTING expert - Coverage, test quality, frameworks
  4. SECURITY expert - Secrets, OWASP, dependencies
  5. PERFORMANCE expert - Bottlenecks, caching, scalability
  6. DOCUMENTATION expert - Coverage, drift, quality
  7. TECHNICAL DEBT expert - TODO/FIXME, code smells
  8. STANDARDS expert - Conventions, error handling, types

Read the full file on GitHub · 160 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. 2d ago First seen · 160 lines · 15 tokens per session scan A 23d58047c382

Subscribe to this mod's changes

reality is a skill published in the GitHub repository fall-out-bug/sdp (19 stars, last pushed 2mo ago), licensed MIT. It adds 15 tokens to every session and 1,150 once invoked, about $0.0001 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 2026-08-30.