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 rules/anshulixyz/multi-agent-loop-kit/05-loop-listeninggit clone --depth 1 https://github.com/anshulixyz/multi-agent-loop-kitWhat 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 | $0.00318 | $0.00318 |
| Opus 5 | $0.00159 | $0.00159 |
| Sonnet 5 | $0.00064 | $0.00064 |
| Haiku 4.5 | $0.00032 | $0.00032 |
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.
What it actually says
Loop listening rules
Every coding agent must read:
LOOP_RADAR.mdagents-status/task-briefs/*.mdagents-status/approvals/*.md- its own journal
Agents may self-select tasks only when:
- The task touches only their owned paths.
- The task aligns with the current build objective.
- The task has no unresolved contract/schema decision.
- The task does not conflict with another open PR.
- 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
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.
- 2d ago First seen · 68 lines · 318 tokens per session scan A 82f2db8523b6
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.
Other cursor rules, from other repositories
cursor_rule_snippet
Latch decision-continuity gate for Cursor projects.
proxyshield-admin
ProxyShield admin UI conventions.
agent-workspace
Repository evidence and validated engineering workflows.
tech-stack
Cursor rule "tech-stack" from yu-iskw/coding-agent-fabric, covering tech stack, pnpm workspace & monorepo best practices, common commands, workspace protocol and dependency management.
less-is-more
Architecture-first, reduction-first workflow for code changes, debugging, refactoring, and cleanup. Use to trace the owning path, prefer no edit and subtraction before additions, replace obsolete behavior instead of layering around it, keep scope closed, refute your own diagnosis and fix before believing them, verify…
api
Prefer named exports.