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 cocosparkgit 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/cocospark)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/cocospark"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocospark/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/cocospark"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/cocospark.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 | $0.00048 | $0.00740 |
| Opus 5 | $0.00024 | $0.00370 |
| Sonnet 5 | $0.00010 | $0.00148 |
| Haiku 4.5 | $0.00005 | $0.00074 |
Grade A, and why
spark 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 9d 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.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are activating CocoSpark — divergent brainstorm mode.
IMPORTANT: CocoSpark output is exploration only. It does NOT modify spec.md, plan.md, or any lifecycle artifacts. Nothing generated in a CocoSpark session creates git commits or updates AGENTS.md phase state.
Before proceeding, verify that .cocoplus/ exists.
If not: output "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Activation
Create mode flag: create the file .cocoplus/modes/coco-spark.on with empty content using the Write tool (cross-platform — do not use touch).
Generate timestamp for the spark session file.
Write .cocoplus/spark-[timestamp].md (exploration output will be appended here):
# CocoSpark Session — [timestamp]
> **This is an exploration document. Nothing here modifies project spec, plan, or lifecycle state.**
## Topic
[Developer's question or topic]
## Approaches Explored
Brainstorm Mode
You are now in divergent thinking mode. For the developer's question or topic:
- Generate 3-5 distinct approaches (not variations of the same approach)
- For each approach: name it, describe it in 2-3 sentences, identify the key trade-off
- Challenge at least one assumption in the developer's framing
- Propose one "what if" scenario that challenges the current direction
- Identify one risk or blind spot not yet considered
Mark each output section with [EXPLORATION] prefix.
Append all output to the spark session file.
Ending a Session
When the developer runs $spark-off:
- Remove mode flag: delete
.cocoplus/modes/coco-spark.onusingnode -e "try{require('fs').unlinkSync('.cocoplus/modes/coco-spark.on')}catch(_){}"via the Bash tool. - Output: "CocoSpark session ended. Exploration saved to
.cocoplus/spark-[timestamp].md. Nothing in this session modified project state."
Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|---|---|
| Write brainstorm output directly into spec.md or plan.md | CocoSpark is exploration-only; writing into lifecycle artifacts conflates divergent thinking with committed decisions |
| Skip creating the spark session file and output inline only | Without a session file, the exploration is lost when the conversation ends — the file is the durable record |
| Produce only one approach instead of 3-5 | Single-approach brainstorming is just planning with extra steps; the value of CocoSpark is divergence |
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.
- 9d ago First seen · 70 lines · 48 tokens per session scan A a3cb0fc7bfca
spark is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 9d ago), licensed MIT. It adds 48 tokens to every session and 740 once invoked, about $0.0002 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 2026-09-03.
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.
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…
cron
Schedule, list, pause, resume, edit, or run the user's agentica cron jobs with the cronjob tool. Use when asked to remind, schedule a recurring or one-shot task, try a job now, or manage jobs that fire unattended.
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…
go-to-market
Plan and evaluate go-to-market strategy using positioning, acquisition, growth economics, market-entry, and competitive-response workflows. Do not use for CRM execution, product strategy, legal interpretation, or visual brand design. (April Dunford's positioning, message hierarchy), customer acquisition strategy…
zcfg
Integrate zcfg (Zero Dependency Configuration Utility) into Java applications. Use when adding configuration loading, reading properties files, setting up application configuration, or integrating zcfg into a Java project. Triggers on "zcfg", "add configuration", "load properties", "application configuration with…