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 alivirgo/Major-AI-Skills --skill compact-enum-mappingsgit clone --depth 1 https://github.com/alivirgo/Major-AI-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/alivirgo/major-ai-skills/compact-enum-mappings)<a href="https://agentmods.dev/skills/alivirgo/major-ai-skills/compact-enum-mappings"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/compact-enum-mappings/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/alivirgo/major-ai-skills/compact-enum-mappings"><img src="https://agentmods.dev/badge/skills/alivirgo/major-ai-skills/compact-enum-mappings.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 | $0.00025 | $0.01277 |
| Opus 5.5 | $0.00010 | $0.00511 |
| Sonnet 5.5 | $0.00005 | $0.00255 |
| Haiku 4.5 | $0.00003 | $0.00128 |
Grade A, and why
compact-enum-mappings 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 148 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Compact Enum & Short-Code Mapping Protocol
Overview
In automated data extraction, log classification, and batch API workflows, models frequently output structured JSON containing long descriptive string identifiers ("transaction_status": "PAYMENT_AUTHORIZATION_PENDING_FRAUD_REVIEW" or "log_severity": "INFRASTRUCTURE_CRITICAL_FAILURE").
Verbose string constants consume 8 to 15 tokens per record. In a batch processing run of 5,000 items, transmitting repetitive string identifiers burns over 60,000 redundant output tokens.
The Compact Enum Mapping Protocol defines a lightweight integer or 1-character codebook in the prompt header, allowing the model to emit 1-token codes (0, 1, 2) that downstream application code deserializes into rich, strongly-typed domain objects.
Verbose String Identifiers vs. Compact Enum Codes
┌─────────────────────────────────────────────────────────────┐
│ Enum Token Serialization │
│ │
│ Verbose String Identifiers (145 Tokens for 3 Records): │
│ [ │
│ {"id": 101, "status": "TRANSACTION_SETTLED_SUCCESSFUL"},│
│ {"id": 102, "status": "TRANSACTION_REJECTED_INSUFFICIENT"}│
│ {"id": 103, "status": "TRANSACTION_PENDING_VERIFICATION"}│
│ ] │
│ │
│ Compact Enum Codes (38 Tokens - 73.8% Reduction!): │
│ Map: { 0: SUCCESS, 1: INSUFFICIENT_FUNDS, 2: PENDING } │
│ [ [101, 0], [102, 1], [103, 2] ] │
└─────────────────────────────────────────────────────────────┘
The Master Compact Enum Prompt Schema
When prompting an LLM to categorize or classify bulk records, inject the codebook at the top:
Classify the sentiment and urgency of the customer messages below.
### 🔑 Codebook Mapping:
- **Category (C)**: `0: Billing`, `1: Tech_Bug`, `2: Feature_Request`, `3: Account_Access`
- **Urgency (U)**: `0: Low`, `1: Medium`, `2: Critical_Outage`
- **Action (A)**: `0: Auto_Reply`, `1: Escalate_L2`, `2: Page_OnCall`
### Input Records:
1. "My server is down and throwing 500 errors on payment routes."
2. "How do I change my credit card on file?"
### Output Format:
Return a compact JSON array of integer tuples: `[[record_id, C, U, A], ...]`
Output JSON only:
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.
- 1mo ago Changed · -23 tokens per session 4ece6e90ddf2
- 1mo ago First seen · 148 lines · 48 tokens per session scan A a3fac9d8b14f
compact-enum-mappings is a skill published in the GitHub repository alivirgo/Major-AI-Skills (2 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 1,277 once invoked, about $0.0001 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 2026-09-05.
Other skills, from other repositories
aws-sst-development
SST v4 (Ion) expert for managing AWS resources as code with the Pulumi-backed framework.
migrating-mastra-to-pydantic-ai
Migrate TypeScript Mastra applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports @mastra/ or relies on Mastra agents, tools, workflows, memory, processors, streaming, approvals, skills, or subagents.
migrating-vercel-ai-sdk-and-eve-to-pydantic-ai
Migrate TypeScript Vercel AI SDK or Eve applications to Python with Pydantic AI and, only when needed, Pydantic AI Harness. Use when source code imports ai, @ai-sdk/, or eve, or relies on generateText, streamText, ToolLoopAgent, useChat, Eve agents, tools, skills, subagents, approvals, sessions, channels, schedules…
migrating-pi-to-pydantic-ai
Migrate TypeScript Pi coding-agent applications, extensions, or packages to Python with Pydantic AI and Pydantic AI Harness. Use when source code imports @earendil-works/pi-, calls createAgentSession, registers Pi extensions, or relies on Pi tools, hooks, skills, sessions, compaction, providers, TUI, RPC, or packages.
aiko-resume
A session-resume skill that reads saved state and recent automatic logs to identify unfinished work. Session state is a record of what was in progress before a restart.
aiko
A session command that starts the Aiko AI agent and loads a chosen personality from a shared folder in the user’s home directory. It keeps that personality active for the rest of the session.