A guided discussion that records key implementation decisions before planning begins, such as the model, evaluation method, accuracy target, and scope.

Use it after writing a project specification to agree on implementation choices, optionally followed by an adversarial review of those choices.

It prevents a planning process from silently guessing decisions that the developer has not approved.

discuss — Skill for Claude Code by Snowflake-Labs/cocoplus

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.

Any agent

npx skills add Snowflake-Labs/cocoplus --skill discuss

Clone the repo

git clone --depth 1 https://github.com/Snowflake-Labs/cocoplus

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/discuss/github.svg)](https://agentmods.dev/skills/snowflake-labs/cocoplus/discuss)

Your own site

<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/discuss"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/discuss/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/discuss"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/discuss.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 54 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,267 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.00054	$0.02267
Opus 5.5	$0.00022	$0.00907
Sonnet 5.5	$0.00011	$0.00453
Haiku 4.5	$0.00005	$0.00227

Measured 20d ago against content hash bf68776f442a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

discuss 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 20d 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/skills/cocodiscuss/discuss/SKILL.md · 239 lines

How it starts

The opening of the file, as written. The whole thing — 239 lines — stays where its author put it; the contents beside it link to each section on GitHub.

$discuss

Run a structured pre-planning dialogue that captures implementation decisions before $plan runs. Prevents the planning agent from silently filling in gaps with choices the developer never consciously made.

Preconditions

.cocoplus/ must be initialized
lifecycle/spec.md must exist (run $spec first)

Arguments

Flag	Effect
(none)	Standard decision wizard
`--red-team`	Standard wizard + adversarial challenge session after PASS gate

--red-team activates after the standard wizard completes with a PASS score (≥9). It loads .cortex/skills/cocodiscuss/discuss-red-team/SKILL.md and runs a non-blocking adversarial challenge session against every discuss.md decision. Advisory only — does not block $plan.

Step-by-Step Behavior

Phase 1 — Read Spec and Determine Context

Verify initialization: Check .cocoplus/ exists. If not, output: "CocoPlus not initialized. Run $pod init first." and exit.
Verify spec.md: Read .cocoplus/lifecycle/spec.md. If not found, output: "Spec phase must complete before $discuss. Run $spec first." and exit.
Detect work type: Analyze spec.md to determine the primary type of work:
- AI Function build: spec mentions AI_COMPLETE, AI_CLASSIFY, AI_EXTRACT, or similar Cortex function development
- Cortex Search: spec mentions search service configuration or retrieval
- Semantic Model: spec mentions Analytics Engineer semantic modeling
- Data Pipeline: spec describes ETL, transformation, or data movement work
Load CocoContext standards (if available): Read .cocoplus/context/approved-models.md, quality-thresholds.md, warehouse-policy.md to pre-populate answers where organizational standards are definitive.

Phase 2 — Structured Decision Wizard

Run the following question set adapted to the work type. For each question:

If CocoContext has a definitive answer (e.g., approved-models.md lists only one approved model), display the standard's answer with attribution and confirm with developer (press Enter to accept or type override)
For open questions, ask clearly and wait for developer response

Read the full file on GitHub · 239 lines

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.

20d ago Changed bf68776f442a
1mo ago First seen · 239 lines · 54 tokens per session scan A 72f993ae49ed

Subscribe to this mod's changes

discuss is a skill published in the GitHub repository Snowflake-Labs/cocoplus (726 stars, last pushed 20d ago), licensed MIT. It adds 54 tokens to every session and 2,267 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-09-03.

Building agents LLM Planning agents agentskills cocoplus cortex cortexai snowflake

prompt-engineering

Master advanced prompt engineering techniques to maximize LLM performance, reliability, and controllability in production. Use when optimizing prompts, improving LLM outputs, designing production prompt templates, or building AI-powered features.

wpank/ai · 44 tokens

create-tech-design

Only use when the user explicitly invokes this skill by name.

humanlayer/humanlayer · 16 tokens

langgraph

LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…

yonatangross/orchestkit · 80 tokens

examples-qa

Verify Instructor behavior through the repository's ./examples/ suite in pass, live record, or hermetic replay mode. Use when running selected examples or the corpus, capturing and reusing recorded LLM HTTP responses, diagnosing hub results, or distinguishing real errors, assertion failures, skipped examples, and…

cognesy/instructor-php · 67 tokens

openkb-html-critic

Use to review a generated HTML deck or single-page artifact for visual quality and structural correctness. Especially good at catching CSS specificity bugs where slide-modifier classes (.divider, .center, .q, .flow etc.) accidentally override the base .slide{display:none} and cause one slide to stack on top of every…

VectifyAI/OpenKB · 132 tokens

terraform

Operate Terraform and OpenTofu across the whole infrastructure lifecycle: module structure, state backends and locking, plan/apply workflow, drift detection, remote state, upgrade and refactor flows, and evidence-based diagnostics. Use when running or inspecting terraform plans, applies, state files, imports, or state…

magnus919/agent-skills · 96 tokens