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 wisdom-insightsgit 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/wisdom-insights)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/wisdom-insights"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/wisdom-insights/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/wisdom-insights"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/wisdom-insights.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 | $0.00054 | $0.01092 |
| Opus 5 | $0.00027 | $0.00546 |
| Sonnet 5 | $0.00011 | $0.00218 |
| Haiku 4.5 | $0.00005 | $0.00109 |
Grade A, and why
wisdom-insights 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 — 99 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Objective
Generate a structured insights report from CocoWisdom rejection history using a Haiku sub-agent synthesis.
Before proceeding, verify that .cocoplus/ exists. If not, output: "CocoPlus is not initialized. Run $pod init first." Then stop.
Step 1 — Read Rejections and Prior Thesis
Read .cocoplus/wisdom/rejections.jsonl. If absent or fewer than 3 records, output: "Not enough rejection data for insights (minimum 3 records needed). Current count: ." Then stop.
Load prior thesis (carry-forward): Glob for insights-*.md files in .cocoplus/wisdom/. If any exist, read the most recent one (by filename date). Extract the ## Thesis section. Store as prior_thesis. If no prior insights file exists, prior_thesis is null (first-run case).
Step 2 — Prepare Analytics Data
Compute the following deterministically before invoking any sub-agent:
- Total records by gate
- Total records by dimension
- Records by dimension for last 30 days vs prior 30 days (trend per dimension)
- Sessions with rejections vs sessions without (from distinct session_ids in record set and recent sessions)
- Most improved dimension (highest reduction in last 30 days)
- Most persistent dimension (most records, no reduction)
Step 3 — Spawn Haiku Synthesis Sub-Agent
Pass the pre-computed analytics data AND prior_thesis to a Haiku sub-agent with this mandate:
"Read the provided rejection analytics data and produce a structured insights report. The report must:
- Name the most frequently blocked dimension and explain the pattern from the evidence (do not speculate — cite actual rejection reasons)
- Describe the quality trend (improving/degrading/stable) with specific session counts
- Produce a per-dimension health table
- Provide 2-3 actionable recommendations based on the patterns observed
Carry-forward thesis rule (mandatory):
- If
prior_thesisis provided: your## Thesissection MUST begin with the prior thesis verbatim, then add a### New Evidencesubsection that extends or refines it based on the new records. Never replace the prior thesis — only extend it. - If
prior_thesisis null (first run): write a fresh## Thesissection. - The thesis is the project's accumulated quality narrative. It must grow incrementally across insight runs, not reset.
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 · 99 lines · 54 tokens per session scan A ddf9b8a43989
wisdom-insights is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 9d ago), licensed MIT. It adds 54 tokens to every session and 1,092 once invoked, about $0.0003 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…