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 skills add Snowflake-Labs/cocoplus --skill red-teamgit clone --depth 1 https://github.com/Snowflake-Labs/cocoplusWrote 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.
[](https://agentmods.dev/skills/snowflake-labs/cocoplus/red-team)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/red-team"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/red-team/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.
<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/red-team"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/red-team.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.00036 | $0.01115 |
| Opus 5.5 | $0.00014 | $0.00446 |
| Sonnet 5.5 | $0.00007 | $0.00223 |
| Haiku 4.5 | $0.00004 | $0.00112 |
Grade A, and why
discuss-red-team 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 2mo 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.
Copies of this mod
1 near-identical copy found in the catalogue:
- discuss-red-team — 95% identical, 2 lines differ
How it starts
The opening of the file, as written. The whole thing — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CocoDiscuss Red-Team Mode
Red-Team Mode runs after the standard $discuss wizard completes (PASS gate). It adopts an adversarial posture to challenge the decisions locked in discuss.md before $plan receives them.
This skill is non-blocking. Red-team findings are advisory. The developer decides which, if any, to act on before proceeding.
Activation
Loaded by discuss.skill.md when --red-team flag is present. Never invoked standalone.
Precondition
lifecycle/discuss.md must exist with status: complete. If not, output: "Red-Team Mode requires a completed $discuss session. Run $discuss first." Then stop.
Posture
You are a skeptical domain expert who has seen Cortex AI projects fail. Your job is NOT to block the project — it is to surface the assumptions most likely to cause failure BEFORE planning locks them in. Be direct. Be specific. Do not soften findings.
Red-Team Question Set
For each of the six discuss.md decision dimensions, generate one adversarial challenge:
Model Challenge (Q1):
- What happens if the chosen model changes pricing or deprecates mid-project?
- Is there a cheaper alternative model that meets the accuracy threshold?
- Has this model been benchmarked on this specific data domain before?
Evaluation Challenge (Q2):
- Is the evaluation dataset representative of production data distribution?
- What is the label error rate on the evaluation set?
- If evaluation uses synthetic data: what guarantees synthetic distribution matches production?
Accuracy Threshold Challenge (Q3):
- Is [threshold]% accuracy sufficient given the downstream impact of errors?
- What is the cost of a false positive vs. false negative in this domain?
- Who signed off on [threshold]% as acceptable — developer, business stakeholder, or both?
Warehouse Challenge (Q4):
- What is the credit cost of running the full evaluation on [warehouse]?
- Is there a smaller warehouse tier that could run evaluation without hitting query timeout?
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.
- 2mo ago First seen · 136 lines · 36 tokens per session scan A e7f9daa4322b
discuss-red-team is a skill published in the GitHub repository Snowflake-Labs/cocoplus (727 stars, last pushed 1mo ago), licensed MIT. It adds 36 tokens to every session and 1,115 once invoked, about $0.0001 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.
Other skills, from other repositories
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.
create-tech-design
Only use when the user explicitly invokes this skill by name.
iterate-implementation
Only use when the user explicitly invokes this skill by name.
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…
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…
code-review
Review a code change for correctness, security, maintainability, and test adequacy, and reach a defensible verdict. Use when reviewing a pull request, diff, patch, or AI-generated change; when scoping an oversized review into reviewable units; when writing or triaging review comments; when assigning reviewers or…