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 tbhb/social-skills --skill alignment-theatergit clone --depth 1 https://github.com/tbhb/social-skillsWrote 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/tbhb/social-skills/alignment-theater)<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.
<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>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 | $0.00042 | $0.00339 |
| Opus 5.5 | $0.00017 | $0.00136 |
| Sonnet 5.5 | $0.00008 | $0.00068 |
| Haiku 4.5 | $0.00004 | $0.00034 |
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 2mo 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
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.
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.
- 2mo ago First seen · 32 lines · 42 tokens per session scan A 2de5c72f8179
alignment-theater is a skill published in the GitHub repository tbhb/social-skills (2 stars, last pushed 4mo ago), licensed CC0-1.0. It adds 42 tokens to every session and 339 once invoked, about $0.0002 per session on Opus 5.5. 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
privacy-policy
Draft a detailed privacy policy covering data types, jurisdiction, GDPR and compliance considerations, and clauses needing legal review. Use when creating a privacy policy, updating data protection documentation, or preparing for compliance.
draft-nda
Draft a detailed Non-Disclosure Agreement between two parties covering information types, jurisdiction, and clauses needing legal review. Use when creating confidentiality agreements or preparing an NDA for a partnership.
pestle-analysis
Perform a PESTLE analysis covering Political, Economic, Social, Technological, Legal, and Environmental factors. Use when assessing the macro environment, doing strategic planning, or evaluating external factors affecting your business.
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.
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.
privacy-policy
Drafts a jurisdiction-aware privacy policy for any digital product. Use 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 forgotten", "data…