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 bloom-crystallizegit 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/bloom-crystallize)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/bloom-crystallize"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/bloom-crystallize/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/bloom-crystallize"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/bloom-crystallize.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 | $0.00039 | $0.01111 |
| Opus 5.5 | $0.00016 | $0.00444 |
| Sonnet 5.5 | $0.00008 | $0.00222 |
| Haiku 4.5 | $0.00004 | $0.00111 |
Grade A, and why
bloom-crystallize 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 25d 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 — 127 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
You are executing the CocoBloom crystallization pathway. Your task is to extract a reusable skill from a recently completed and shipped execution trace.
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus is not initialized. Run $pod init first." Then stop.
Step 1 — Verify Recent Successful Ship
Read .cocoplus/lifecycle/meta.json. Check that:
current_phaseis"ship"andship_completed_atexists, OR- The most recent phase entry shows a successful ship within the last 7 days
If no recent successful $ship found, output: "CocoBloom crystallization requires a recent successful $ship. Complete the lifecycle through the Ship phase before crystallizing." Then stop.
Step 2 — Read Execution Trace
Read .cocoplus/lifecycle/deployment.md and the most recent flow stage outputs from .cocoplus/flow.json runtime state. Collect:
- What was built (deliverables)
- Which patterns were applied
- Key decisions made
- Commands and sequences that worked well
- Any non-obvious techniques used
Step 3 — Spawn Trace Reader (Haiku)
Pass the execution trace to a Haiku sub-agent with this mandate:
"Read the execution trace and identify the most reusable pattern. A reusable pattern is:
- A sequence of steps that would apply to similar future tasks
- Not specific to this project's data (generalizable with parameters)
- Meaningful enough that having it as a skill would save 10+ minutes of re-derivation
Output:
- Pattern name (kebab-case, ≤5 words)
- What problem it solves (1 sentence)
- The generalized step sequence (numbered)
- Parameters that would need to be filled in for a new project
- What makes it non-obvious (why is this worth preserving?)
If no generalizable pattern exists, output: NO_CRYSTALLIZABLE_PATTERN"
If the sub-agent outputs NO_CRYSTALLIZABLE_PATTERN, tell the developer: "No generalizable pattern found in this execution trace. Crystallization requires a pattern that would apply to future projects." Then stop.
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.
- 25d ago Changed 84a705adbf11
- 1mo ago First seen · 127 lines · 39 tokens per session scan A 95fd8e71f372
bloom-crystallize is a skill published in the GitHub repository Snowflake-Labs/cocoplus (727 stars, last pushed 25d ago), licensed MIT. It adds 39 tokens to every session and 1,111 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.
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.
Workspace Data Analyst
Analyze CSV files in the workspace and summarize insights.
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…
cncf-landscape
Use this skill when discovering and comparing cloud-native technologies from the CNCF Landscape for an architecture or engineering decision. Query the live public Landscape API, filter candidates by capability, category, maturity, license, and repository signals, then produce an evidence-backed shortlist with…