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 agentmods add commands/voxtechnologies/anty-framework/rulesgit clone --depth 1 https://github.com/VoxTechnologies/anty-frameworkWhat 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 | $0.00010 | $0.00542 |
| Opus 5 | $0.00005 | $0.00271 |
| Sonnet 5 | $0.00002 | $0.00108 |
| Haiku 4.5 | $0.00001 | $0.00054 |
Grade A, and why
rules 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 yesterday.
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:
- rules — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/anty:rules — View/Edit User Rules
Trigger
User runs /anty:rules
Behavior
Read and display the contents of .anty/rules.md, then allow the user to view, add, modify, or remove rules. Rules are injected into every agent interaction with the highest priority.
Default View (no arguments)
- Read
.anty/rules.md - Display current rules with numbered list:
==================================================== USER RULES ==================================================== Rules are injected into every agent interaction with HIGHEST priority. Agents must follow these. ==================================================== 1. [rule text] 2. [rule text] 3. [rule text] ... ==================================================== Commands: "add [rule]" — Add a new rule "edit [n]" — Edit rule number n "remove [n]" — Remove rule number n "done" — Exit rules editor ====================================================
Adding a Rule
When user says "add [rule text]":
- Append the new rule to
.anty/rules.md - Display updated rules list
- Confirm: "Rule added: [rule text]"
Editing a Rule
When user says "edit [n]":
- Display current rule #n
- Ask user for new text
- Replace rule #n in
.anty/rules.md - Display updated rules list
- Confirm: "Rule #[n] updated."
Removing a Rule
When user says "remove [n]":
- Display rule #n and ask for confirmation
- On confirmation, remove rule #n from
.anty/rules.md - Renumber remaining rules
- Display updated rules list
- Confirm: "Rule #[n] removed."
Rules Format in .anty/rules.md
# User Rules
These rules have the HIGHEST priority and override all other instructions.
1. [rule text]
2. [rule text]
3. [rule text]
Edge Cases
- If
.anty/rules.mddoes not exist, create it with the header template - If file exists but has no rules, display "No rules set. Use 'add [rule]' to create your first rule."
- Preserve any markdown formatting within rule text
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.
- yesterday First seen · 82 lines · 10 tokens per session scan A 2cddc7f03146
rules is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 10 tokens to every session and 542 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.
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.