canary-protocol

canary-protocol is a cursor rule for coding agents from devon-clarkk/canary-mcp. It costs 1,098 tokens per session, scanned A, original, no licence file.

Always-on conversation rules for maintaining continuity across turns. They require the agent to create and repeat special keys and anchors, and to answer certain continuity checks.

In plain words
What is it for?
Applying continuity checks and tracking conversation state while an agent interacts with a person.
Why use it?
They provide a way to detect whether conversation context is being retained or lost during a long exchange.

Cursor rule

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/devon-clarkk/canary-mcp/canary-protocol
Clone the repo
git clone --depth 1 https://github.com/devon-clarkk/canary-mcp

Wrote 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.

agentmods badge for canary-protocol

README.md
[![agentmods](https://agentmods.dev/badge/rules/devon-clarkk/canary-mcp/canary-protocol.svg)](https://agentmods.dev/rules/devon-clarkk/canary-mcp/canary-protocol)
Your own site
<a href="https://agentmods.dev/rules/devon-clarkk/canary-mcp/canary-protocol"><img src="https://agentmods.dev/badge/rules/devon-clarkk/canary-mcp/canary-protocol.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,098 This file is loaded in full into every session.
When invoked 1,098 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin unknown 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 $0.01098 $0.01098
Opus 5 $0.00549 $0.00549
Sonnet 5 $0.00220 $0.00220
Haiku 4.5 $0.00110 $0.00110

Measured 3d ago against content hash 4431af517688, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

canary-protocol 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 3d 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.

skills/cursor/canary-protocol.mdc · 46 lines

The source is not reproduced here

No licence file

A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.

Read it on GitHub

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. 3d ago First seen · 46 lines · 1,098 tokens per session scan A 4431af517688

Subscribe to this mod's changes

canary-protocol is a cursor rule published in the GitHub repository devon-clarkk/canary-mcp (0 stars, last pushed 2mo ago), with no licence file. It adds 1,098 tokens to every session, about $0.0055 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.