loop

A recurring scan command that runs the Anty analysis on a schedule, such as every 30 minutes or every hour, during a Claude Code session.

In plain words
What is it for?
Use it to monitor the business state continuously, receive recovery action proposals for warnings, and stop the scan when needed.
Why use it?
It reduces the need to remember repeated checks and can surface problems as they appear. Findings and scan history are saved in the .anty files.

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/loop
Clone the repo
git clone --depth 1 https://github.com/VoxTechnologies/anty-framework
Per session 8 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 819 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 $0.00008 $0.00819
Opus 5 $0.00004 $0.00409
Sonnet 5 $0.00002 $0.00164
Haiku 4.5 $0.00001 $0.00082

Measured yesterday against content hash 552f918751ba, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

loop 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

  • loop — 100% identical, 0 lines differ
commands/loop.md · 109 lines

How it starts

The opening of the file, as written. The whole thing — 109 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/anty:loop — Persistent Operation

Trigger

User runs /anty:loop [interval]

Arguments

  • /anty:loop 30m — Run scan every 30 minutes
  • /anty:loop 1h — Run scan every hour
  • /anty:loop 2h — Run scan every 2 hours
  • /anty:loop stop — Stop the running loop

Behavior

Establish a persistent scan loop that repeatedly executes /anty:scan at the specified interval. Uses the loop skill pattern for continuous operation within a Claude Code session.

Starting the Loop

  1. Parse the interval argument (e.g., 30m, 1h, 2h)
  2. Validate interval is between 10m and 24h
  3. Display confirmation:
    Anty loop started.
    Interval: [interval]
    Next scan: [timestamp]
    Use /anty:loop stop to end.
    
  4. Begin the loop cycle

Loop Cycle

Each iteration:

  1. Read state: Load all .anty/ files to get current state
  2. Execute scan: Run the full /anty:scan 10-point analysis
  3. Evaluate findings:
    • If issues found with severity >= warning:
      • Generate recovery Action proposals
      • Notify user with a summary of findings
    • If no issues: log clean scan silently
  4. Save results: Write scan results to .anty/history/scans/[date].yaml
  5. Append to scratchpad: Add scan summary to .anty/scratchpad.md
  6. Wait: Sleep for the specified interval
  7. Repeat: Go to step 1

Notification Thresholds

Only notify the user (interrupt their work) when:

  • Buffer zone transitions (GREEN->YELLOW, YELLOW->RED)
  • Pipeline deal stalls detected (2x average dwell time)
  • Failure pattern detected (3+ consecutive failures)
  • Anti-pattern detected
  • Growth rate drops below 5%/week
  • Environmental disruption risk detected
  • Oscillation pattern detected

For non-critical findings, accumulate and report at next user interaction.

Notification Format

----------------------------------------------------
ANTY LOOP — [timestamp]
----------------------------------------------------
[severity] [check name]: [one-line summary]

[n] recovery proposals generated.
Run /anty:actions to review.
----------------------------------------------------

Read the full file on GitHub · 109 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. yesterday First seen · 109 lines · 8 tokens per session scan A 552f918751ba

Subscribe to this mod's changes

loop is a command published in the GitHub repository VoxTechnologies/anty-framework (6 stars, last pushed 4mo ago), licensed MIT. It adds 8 tokens to every session and 819 once invoked, about $0.0000 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.