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 patterns-promotegit 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/patterns-promote)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/patterns-promote"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/patterns-promote/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/patterns-promote"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/patterns-promote.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 | $0.00043 | $0.01414 |
| Opus 5 | $0.00022 | $0.00707 |
| Sonnet 5 | $0.00009 | $0.00283 |
| Haiku 4.5 | $0.00004 | $0.00141 |
Grade A, and why
patterns-promote 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 7d 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to promote a CocoCupper finding to a CocoGrove pattern.
Before proceeding, verify that .cocoplus/ exists.
If not: output "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
$grove score <pattern-id> — Promotion Scoring (Durability × Impact × Scope)
Before any promotion is confirmed, run invoke cocogrove/grove-score --id <pattern-id> (or run this scoring interactively when invoked directly as $grove score). Score the candidate pattern on three dimensions, each zero to three:
- Durability — 0: one-time fix · 1: temporary workaround · 2: stable pattern · 3: architectural truth. Assesses whether the pattern remains valid for 30+ days and across schema/data changes.
- Impact — 0: nice-to-know · 1: saves a minute · 2: prevents mistakes · 3: prevents breakage.
- Scope — 0: one file only · 1: one directory · 2: entire CocoPod · 3: all CocoPods of this type.
Decision thresholds:
- Total ≥ 6 → promote (move to CocoSkill or convention store)
- Total 4–5 → watch (revisit next review cycle)
- Total ≤ 3 → ignore (leave in capture store or delete if stale)
- Override: a score of 3 on any single dimension is a strong promotion candidate regardless of total — any architectural truth, any breakage-preventing finding, or any CocoPod-universal pattern requires explicit human review before demotion, even if the total would otherwise suggest "watch" or "ignore".
Display the scoring summary and decision threshold result before promotion is confirmed:
CocoGrove Promotion Score — [pattern-id]
Durability: [0-3] Impact: [0-3] Scope: [0-3] Total: [N]
Decision: PROMOTE | WATCH | IGNORE [+ override note if a single-dimension 3 applies]
Distillation Rules
Apply all three before writing any convention entry — these are mandatory text transformations, not style preferences:
- Descriptive-to-prescriptive — the text must be a direct instruction, not an observation. ("This project uses pnpm" → "Use pnpm install, not npm.")
- Verbose-to-concise — completable in two sentences or fewer; longer explanation belongs in a linked reference file, not the convention entry itself.
- Conditional-to-absolute — hedging language ("sometimes", "might", "can", "it depends") must resolve to a specific condition or be removed. A hedging entry is a note to self, not an instruction.
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.
- 7d ago First seen · 112 lines · 43 tokens per session scan A 95b1a3920bc1
patterns-promote is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 7d ago), licensed MIT. It adds 43 tokens to every session and 1,414 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…