actions

A decision-review command that presents proposed business actions one at a time as three choices and records the founder's selections and results.

In plain words
What is it for?
Use it to review pending marketing or sales actions generated from the founder's business context.
Why use it?
It turns a long list of recommendations into focused decisions. Stored choices help the system learn the founder's preferences over time.

Command

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 commands/voxtechnologies/anty-framework/actions
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/anty-framework
Per session 16 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,002 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 $0.00016 $0.02002
Opus 5 $0.00008 $0.01001
Sonnet 5 $0.00003 $0.00400
Haiku 4.5 $0.00002 $0.00200

Measured 2d ago against content hash 8e4009ea13ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

actions 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • actions — 100% identical, 0 lines differ
commands/actions.md · 213 lines

How it starts

The opening of the file, as written. The whole thing — 213 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/anty:actions — 3-Option Choice Approval with Nudge Architecture

Purpose

Present pending action proposals as structured 3-option choices, using behavioral nudge architecture to support high-quality decisions. Record choices to build the founder's preference profile over time.

Prerequisites

  1. .anty/business-context.yaml must exist. If not: "Run /anty:onboard first."
  2. .anty/actions/ directory must contain at least one action file with status: proposed. If no pending actions: "No pending actions to review. Run /anty:plan to generate strategy and action proposals."

Step 1: Load Context

Read the following files to build decision context:

  • .anty/business-context.yaml (founder's business context)
  • .anty/learning/preferences.yaml (if exists — accumulated preference distributions)
  • .anty/learning/choice-history.yaml (if exists — past choices)
  • .anty/learning/performance-labels.yaml (if exists — past action outcomes)
  • All files in .anty/actions/ with status: proposed

Step 2: For Each Pending Action

Process each proposed action one at a time. Never present multiple action decisions simultaneously.

2a: RECAP (Relevant Context and Priming)

Before presenting options, surface the founder's own data. This is NOT the agent's opinion — it is a mirror of what the founder has already said and what the data shows.

Format:

--- Your Context ---
Business: [product description from business-context]
Current traction: [key metrics from business-context or recent scans]
Strategic mode: [effectuation/causation/hybrid]
Distribution tier: [tier from business-context]
Pain classification: [painkiller/vitamin]
[Any relevant recent performance data from scans or action outcomes]
---

2b: Present 3 Options

Each option must include:

Option A: [Title]
  What: [Clear description of the action]
  Expected timeline: [How long this will take]
  Expected results: [Quantified outcome — be specific]
  Cost: [Money, time, effort required]
  Time required: [Hours per week or total hours]
  First step: [Channel factor — the concrete, immediate next action]

Option B: [Title]
  [Same structure]

Option C: [Title]
  [Same structure]

Read the full file on GitHub · 213 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 · 213 lines · 16 tokens per session scan A 8e4009ea13ba

Subscribe to this mod's changes

actions is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 16 tokens to every session and 2,002 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 2026-08-31.