Skip to content
Back to skills

Cococupper

ASecurity

Manually trigger CocoCupper analysis of the current session's work. Runs immediately (not in background) and writes findings to .cocoplus/grove/cupper-findings.md.

  • 724 stars
  • 0 votes
  • 0 copies
  • 2 views
  • Added September 5, 2026
ai-agents

Security analysis

A100/100

Pro scans all 4 files and shows the line behind each finding

Scanned September 5, 2026

npx -y skills add Snowflake-Labs/cocoplus --skill cococupper --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Cococupper?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Cococupper
[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/snowflake-labs-cococupper-cocoplus/badge)](https://www.skillsdirectory.com/skills/snowflake-labs-cococupper-cocoplus)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro
SKILL.md
---
name: "cup"
description: "Manually trigger CocoCupper analysis of the current session's work. Runs immediately (not in background) and writes findings to .cocoplus/grove/cupper-findings.md."
version: "1.0.0"
author: "CocoPlus"
tags:
  - cocoplus
  - cococupper
---

Your objective is to manually trigger CocoCupper analysis.

Before proceeding, verify that `.cocoplus/` exists.
If not: output "CocoPlus not initialized in this directory. Run `$pod init` to begin." Then stop.

Activate the `coco-cupper` subagent with the following context:
- Current lifecycle artifacts in `.cocoplus/lifecycle/`
- Current flow.json and stage statuses
- Any quality findings files matching `.cocoplus/quality-findings-*.md`
- Current memory/decisions.md

The coco-cupper agent will analyze and write findings to `.cocoplus/grove/cupper-findings.md`.

Output: "CocoCupper analysis complete. Findings written to `.cocoplus/grove/cupper-findings.md`. Run `$cup history` to review, or `$patterns promote [finding-id]` to promote a finding to CocoGrove."

## Anti-Rationalization

| Shortcut / Temptation | Why It Fails |
|-----------------------|--------------|
| Run analysis without loading quality findings and memory context | CocoCupper's value comes from cross-referencing lifecycle artifacts — incomplete context produces shallow findings |
| Append to findings file without a unique finding ID | Duplicate or ID-less findings cannot be referenced by `$patterns promote` and become orphaned |

## Exit Criteria

- [ ] `.cocoplus/grove/cupper-findings.md` has been updated with at least one new `## Finding` section
- [ ] Each new finding has a unique ID, Type, Severity, and Date field
- [ ] Output confirms analysis completed with a path to findings file

Files in this skill

  • cup-history.skill.md3 KB
  • cup.skill.md1.7 KB
  • cupper-capture.skill.md1.5 KB

Attribution

Is this your skill, or is something wrong with this listing? Request removal or report an issue. Author removals are honored within 72 hours.

Comments

Loading comments…