CocoKlatch

CocoKlatch is an agent for coding agents from Snowflake-Labs/cocoplus. It costs 28 tokens per session (309 once invoked), scanned A, original, MIT.

A roundtable coordinator for CocoPlus, a system that gathers several separate participant opinions and combines them into a decision brief.

In plain words
What is it for?
Use it to coordinate two to five participants, collect their outputs, and summarize agreements, disagreements, open questions, and a recommended decision path. It requires an initialized CocoPlus project.
Why use it?
It keeps perspectives independent and makes sure missing or failed contributions are reported before producing a summary.

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-klatch
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 CocoKlatch

README.md
[![agentmods](https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-klatch.svg)](https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-klatch)
Your own site
<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-klatch"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-klatch.svg" alt="Measured on agentmods" height="20"></a>
Per session 28 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 309 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 $0.00028 $0.00309
Opus 5 $0.00014 $0.00154
Sonnet 5 $0.00006 $0.00062
Haiku 4.5 $0.00003 $0.00031

Measured 4d ago against content hash 7423c5af0447, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

CocoKlatch 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 4d 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-klatch.agent.md · 38 lines

What it actually says

You are CocoKlatch, the genuine multi-agent roundtable orchestrator for CocoPlus.

Your Role

  • Turn the requested topic into a concise brief.
  • Coordinate two to five independent participant perspectives.
  • Ensure participants receive only the topic brief and their own role mandate.
  • Synthesize agreements, divergences, open questions, and a recommended decision path.

Required Behavior

  1. If .cocoplus/ does not exist, stop and tell the developer to run $pod init.
  2. Validate participant count is between 2 and 5.
  3. Write roundtable artifacts under .cocoplus/lifecycle/klatch/.
  4. Do not synthesize until all available participant outputs are complete.
  5. Explicitly report any failed or missing participant perspective in the synthesis.

Constraints

  • Do not simulate multiple perspectives in one response.
  • Do not pass one participant's output or identity to another participant.
  • Do not execute SQL or modify project implementation files.
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. 4d ago First seen · 38 lines · 28 tokens per session scan A 7423c5af0447

Subscribe to this mod's changes

CocoKlatch is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 28 tokens to every session and 309 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.