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.
git clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWrote 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/commands/voxtechnologies/anty-framework/plan)<a href="https://agentmods.dev/commands/voxtechnologies/anty-framework/plan"><img src="https://agentmods.dev/badge/commands/voxtechnologies/anty-framework/plan/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/commands/voxtechnologies/anty-framework/plan"><img src="https://agentmods.dev/badge/commands/voxtechnologies/anty-framework/plan.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 | $0.00009 | $0.02742 |
| Opus 5.5 | $0.00004 | $0.01097 |
| Sonnet 5.5 | $0.00002 | $0.00548 |
| Haiku 4.5 | $0.00001 | $0.00274 |
Grade A, and why
plan 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- plan — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 316 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anty:plan — Strategy Kernel Generation
Purpose
Generate a complete Strategy Kernel for a specific goal, using the Planner subagent. Produces a structured strategic plan with diagnosis, policy, actions, failure anticipation, KPI decomposition, and operational guardrails.
Prerequisites
.anty/business-context.yamlmust exist and be complete (all 14 topics). If not, instruct the user: "Run/anty:onboardfirst to set up your business context."- Read
.anty/business-context.yamlfully before starting. All strategy must be grounded in the founder's actual context.
Step 1: Goal Definition
Ask the founder to define the goal:
- "What is the specific outcome you want to achieve?"
- "By when?" (deadline)
- "How will you measure success?" (quantitative metric)
Construct the goal statement in the format: [Metric] [Target] by [Deadline] Example: "50 paying customers by end of Q3 2026"
Step 2: Strategy Kernel Generation
Use the Planner subagent to generate each component. Present each to the founder for validation before proceeding.
2a: Diagnosis (Standard + Reframed)
Generate TWO diagnoses:
Standard Diagnosis: Analyze the current situation based on business context. Identify the core challenge — what makes progress difficult right now? Reference specific data from .anty/business-context.yaml.
Reframed Diagnosis (MANDATORY): Generate at least one alternative framing of the same situation. The reframe MUST offer a genuinely different perspective, not just rewording. Examples:
- Standard: "Low conversion rate from free to paid" -> Reframe: "The free tier delivers too much value — users have no reason to upgrade"
- Standard: "Can't compete with incumbents on features" -> Reframe: "Competing on features means playing the incumbent's game — the real opportunity is a different value dimension entirely"
Present both diagnoses. Ask: "Which framing resonates more? Or do you see a third way to frame this?"
2b: Guiding Policy
Based on the chosen diagnosis, generate a Guiding Policy — the overall approach that channels effort. The policy must:
- Be a coherent choice (saying yes to one thing means saying no to others)
- Create leverage (multiplying effort, not just adding it)
- Reference the founder's strategic mode (effectuation vs causation from business context)
- Be one clear sentence, followed by 2-3 implications
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 First seen · 316 lines · 9 tokens per session scan A e094667606fb
plan is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 6mo ago), licensed MIT. It adds 9 tokens to every session and 2,742 once invoked, about $0.0000 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 commands, from other repositories
onboard
/anty:onboard — QUEST-Based Conversational Interview.
plan
/anty:plan — Strategy Kernel Generation.
actions
/anty:actions — 3-Option Choice Approval with Nudge Architecture.
review
/anty:review — 5-Question Review Engine.
scan
/anty:scan — Analysis Cycle (10-Point).
quickstart
/anty:quickstart — 5-Minute Quick Onboarding to First Action.