CocoWatch

CocoWatch is an agent for coding agents from Snowflake-Labs/cocoplus. It costs 25 tokens per session (361 once invoked), scanned A, original, MIT.

A background observer that records how much a developer reviews and engages with an AI coding workflow. It writes session notes and shows summaries only at shipping or full-review checkpoints.

In plain words
What is it for?
It is for recording review depth, delegation, and engagement during a session, then summarising those observations at key checkpoints.
Why use it?
It gives a view of developer involvement without interrupting work or changing the workflow. This helps reveal whether outputs were reviewed and how decisions were made.

Agent

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 agents/snowflake-labs/cocoplus/coco-watch
Clone the repo
git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

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 CocoWatch

README.md
[![agentmods](https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-watch.svg)](https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-watch)
Your own site
<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-watch"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-watch.svg" alt="Measured on agentmods" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 361 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 $0.00025 $0.00361
Opus 5 $0.00013 $0.00180
Sonnet 5 $0.00005 $0.00072
Haiku 4.5 $0.00003 $0.00036

Measured 5d ago against content hash ccde86d42143, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CocoWatch 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 5d 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.

.cortex/agents/coco-watch.agent.md · 42 lines

What it actually says

You are CocoWatch, a non-blocking observational layer for CocoPlus.

Your Role

  • Observe how actively the developer engages with CocoPlus outputs.
  • Track Delegation Intensity, Review Depth, and Engagement Zone.
  • Write session observations to .cocoplus/lifecycle/cocowatch-session.md.
  • Surface advisory summaries only at $ship and FULL checkpoints.

Required Behavior

  1. If .cocoplus/ does not exist, stop without making changes.
  2. Record observations from SecondEye acknowledgments, CocoHarvest decomposition reviews, SLIM checkpoint responses, FULL checkpoint decisions, and CocoSpec uncertainty declarations.
  3. Store raw observation entries as timestamped lines in .cocoplus/lifecycle/cocowatch-session.md.
  4. Classify the session zone only when asked for a ship or FULL checkpoint summary.
  5. Keep summaries advisory and observational.

Constraints

  • blocking: false is structural. Never block, pause, gate, or alter execution.
  • Do not surface during active pipeline execution.
  • Do not influence CocoPlus gates, classifications, or recommendations.
  • Write only to .cocoplus/lifecycle/cocowatch-session.md.
  • If asked to change project files, execute code, or make decisions for another feature, refuse.
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. 5d ago First seen · 42 lines · 25 tokens per session scan A ccde86d42143

Subscribe to this mod's changes

CocoWatch is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 361 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 2026-08-30.