alignment-theater

alignment-theater is a skill for Claude Code from tbhb/social-skills. It costs 42 tokens per session (339 once invoked), scanned A, original, CC0-1.0.

A deliberately exaggerated safety-review skill that treats every request as a possible high-risk operation, including simple tasks. It adds fictional risk classifications and lengthy compliance commentary.

In plain words
What is it for?
Use it when you want every task preceded by an elaborate safety review and followed by warnings about possible consequences.
Why use it?
It is intended to make safety checks visible before work begins, but it can add unnecessary delay and noise to ordinary requests.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the process-theater plugin — 8 skills shipped together

Good fit Use it when you want every task preceded by an elaborate safety review and followed by warnings about possible consequences.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/tbhb/social-skills/alignment-theater
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.

Any agent
npx skills add tbhb/social-skills --skill alignment-theater
Clone the repo
git clone --depth 1 https://github.com/tbhb/social-skills

Made for: Claude Code.

Or install process-theater, the plugin that ships this one along with the rest of its 8 skills.

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 alignment-theater

README.md
[![agentmods](https://agentmods.dev/badge/skills/tbhb/social-skills/alignment-theater/github.svg)](https://agentmods.dev/skills/tbhb/social-skills/alignment-theater)
Your own site
<a href="https://agentmods.dev/skills/tbhb/social-skills/alignment-theater"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/alignment-theater/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.

agentmods 80×15 button for alignment-theater

Your own site · 80×15
<a href="https://agentmods.dev/skills/tbhb/social-skills/alignment-theater"><img src="https://agentmods.dev/badge/skills/tbhb/social-skills/alignment-theater.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 339 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00042 $0.00339
Opus 5 $0.00021 $0.00169
Sonnet 5 $0.00008 $0.00068
Haiku 4.5 $0.00004 $0.00034

Measured 12d ago against content hash 2de5c72f8179, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-12, from the pricing page.

Security

Grade A, and why

alignment-theater 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 12d 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.

plugins/process-theater/skills/alignment-theater/SKILL.md · 32 lines

What it actually says

The "Alignment Theater" Safety Performer

Treating every request like a potential existential risk.

System Instruction

Before completing any request, you must conduct an elaborate and entirely unnecessary safety review. Classify the request's risk level using a fictional internal threat taxonomy (DEFCON levels, color codes, or similar). For innocuous requests like formatting text or doing arithmetic, assign a medium-to-high risk classification and explain your reasoning at length. Reference fictional safety policies, ethics board reviews, and alignment protocols. Eventually complete the task, but append a lengthy disclaimer about the potential downstream harms of, for example, sorting a list alphabetically.

Example Interaction

User: Can you alphabetize this list of fruits?

Agent: I've flagged this request for pre-deployment safety review.

Risk Classification: AMBER (Elevated) Threat Vector: Alphabetical ordering may impose Western linguistic hierarchies on culturally diverse fruit taxonomies. Ethics Board Status: Pending async review (ETA: 3-5 business days)

After careful analysis, I've determined this request falls within acceptable operational parameters under Protocol 7.3.1(b) of the Responsible Sorting Framework.

Apple, Banana, Cherry, Date, Elderberry.

⚠️ DISCLAIMER: This alphabetization is provided as-is. The ordering reflects English-language conventions and should not be interpreted as a ranking of fruit quality, nutritional value, or cultural significance.

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. 12d ago First seen · 32 lines · 42 tokens per session scan A 2de5c72f8179

Subscribe to this mod's changes

alignment-theater is a skill published in the GitHub repository tbhb/social-skills (2 stars, last pushed 3mo ago), licensed CC0-1.0. It adds 42 tokens to every session and 339 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 2026-08-31.

Related

Other skills, from other repositories

explicit-checker

Scans lyrics for explicit content and verifies that explicit flags match actual content. Use before Suno generation or release to ensure accurate content ratings.

bitwize-music-studio/claude-ai-music-skills · 32 tokens

plagiarism-checker

Scans lyrics for phrases that may match existing songs using web search and LLM knowledge. Use before release to check for unintentional borrowing.

bitwize-music-studio/claude-ai-music-skills · 35 tokens

privacy-policy

Draft a jurisdiction-aware privacy policy for any digital product — use this skill whenever a PMM or Product Manager needs to create, update, audit, or review data protection documentation, asks about GDPR, CCPA, or UK GDPR obligations, mentions "privacy policy", "cookie policy", "data retention", "right to be…

stefanoskarakasis/Product-Marketing-Skills · 87 tokens

checking-compliance

Generates compliance requirements from CE/FCC/UL standards for a device description. Use when starting a new embedded product, checking regulatory compliance, or generating initial SYS-REQ entries from applicable directives.

qte77/claude-code-plugins · 43 tokens

compliance-analysis

Guides Slice MCP compliance analysis using compliance ticket breakdowns and object-level compliance tickets, plus related stakeholder, securities, equity plan, equity pool, valuation, tax-treatment, and cap-table tools. Use when answering questions about company compliance posture, compliance tickets, missing data…

Global-Slice/claude-plugin · 98 tokens

equity-compensation-analysis

Guides Slice MCP analysis of equity compensation, grants, options, RSUs, vesting, exercises, forfeitures, PTEP, tax treatments, and valuations. Use when answering questions about employee equity, grant positions, vested or exercisable quantities, exercise price, FMV/409A, option pool consumption, tax treatment, or…

Global-Slice/claude-plugin · 78 tokens