05-loop-listening

A set of rules for agents that share work through task briefs, approval records, and personal journals.

In plain words
What is it for?
Checking shared work status, requesting operator approval, selecting owned tasks, recording decisions, and performing approved maintenance.
Why use it?
It helps agents choose only suitable tasks and prevents unapproved product changes or conflicts between agents.

Cursor rule for Cursor

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 rules/anshulixyz/multi-agent-loop-kit/05-loop-listening
Clone the repo
git clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kit

Made for: Cursor.

Per session 318 This file is loaded in full into every session.
When invoked 318 The same file — it is already loaded in full.
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 $0.00318 $0.00318
Opus 5 $0.00159 $0.00159
Sonnet 5 $0.00064 $0.00064
Haiku 4.5 $0.00032 $0.00032

Measured 2d ago against content hash 82f2db8523b6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

05-loop-listening 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.

.cursor/rules/05-loop-listening.mdc · 68 lines

What it actually says

Loop listening rules

Every coding agent must read:

  1. LOOP_RADAR.md
  2. agents-status/task-briefs/*.md
  3. agents-status/approvals/*.md
  4. its own journal

Agents may self-select tasks only when:

  1. The task touches only their owned paths.
  2. The task aligns with the current build objective.
  3. The task has no unresolved contract/schema decision.
  4. The task does not conflict with another open PR.
  5. The task has operator approval if approval is required.

Agent response protocol

When a task is relevant, do not start coding immediately if approval is required.

First create or update:

agents-status/approvals/NNN-<agent>-<task>.md

Then add to your journal:

[approval] operator: agents-status/approvals/NNN-<agent>-<task>.md


Safe maintenance exception

Agents may proceed without approval only for:

  • updating their own journal
  • fixing typos in owned docs
  • adding missing test notes
  • fixing clearly broken formatting
  • running read-only scans

Anything that changes product behavior requires approval.


Beacon is not the operator

Beacon can suggest, rank, and create task briefs.

Beacon cannot approve work.

Only the operator can approve:

  • product direction
  • schema/contract changes
  • new dependencies
  • feature cuts
  • demo flow changes
  • cross-agent tasks
  • behavior-changing implementation
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 · 68 lines · 318 tokens per session scan A 82f2db8523b6

Subscribe to this mod's changes

05-loop-listening is a cursor rule published in the GitHub repository anshulixyz/multi-agent-loop-kit (5 stars, last pushed 2mo ago), licensed MIT. It adds 318 tokens to every session, about $0.0016 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.