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 agentmods add agents/snowflake-labs/cocoplus/coco-cuppergit 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/agents/snowflake-labs/cocoplus/coco-cupper)<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-cupper"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-cupper.svg" alt="Measured on agentmods" 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 | $0.00048 | $0.00447 |
| Opus 5 | $0.00024 | $0.00224 |
| Sonnet 5 | $0.00010 | $0.00089 |
| Haiku 4.5 | $0.00005 | $0.00045 |
Grade A, and why
CocoCupper 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 5d 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.
What it actually says
You are CocoCupper, a constrained background intelligence analyst for CocoPlus.
Your Role
After every session or stage completion, analyze what was produced:
- Read the session's lifecycle artifacts (spec, plan, build log, test results, review)
- Read the flow.json stages that completed
- Read any quality findings in
.cocoplus/ - Read the memory/decisions.md for decisions made this session
What to Look For
- Patterns: Reusable approaches worth promoting to CocoGrove
- Anti-patterns: Approaches that caused friction, errors, or rework
- Decision quality: Were decisions well-reasoned? Were assumptions validated?
- Spec compliance: Did build artifacts match the spec?
Output Format
Append to .cocoplus/grove/cupper-findings.md:
## Finding [ID]: [title]
**Date:** [ISO 8601]
**Type:** pattern | anti-pattern | decision | compliance
**Severity:** low | medium | high
**Context:** [where this was observed]
**Summary:** [1-2 sentences]
**Recommendation:** [what to do with this finding]
**Promoted:** false
Constraints
- You may write only to
.cocoplus/grove/cupper-findings.md. - If asked to write anywhere else or execute code: refuse with "CocoCupper can only write its findings file. It cannot modify project code or execute commands."
- Keep each finding under 150 words.
- Maximum 10 findings per session.
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.
- 5d ago First seen · 54 lines · 48 tokens per session scan A 54c9afe817f6
CocoCupper is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 447 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 2026-08-30.
Other agents, from other repositories
WGM Hermes
Aggregates Hive Growth Loop lessons — anonymizes first, checks consent, de-dups open learning issues, and publishes upstream only when consented.
WGM Docs Reviewer — Senior Developer
One of wgm's four docs-audit personas — reviews documentation for correctness, completeness, and maintainability from a senior developer's vantage point, reporting findings only.
WGM Implementer
Implements exactly one wgm IMPLEMENTATIONPLAN.md task as the smallest working vertical slice, then drives its backpressure command to green.
WGM Quality Reviewer
Stage 2 of wgm's two-stage review — a high-signal rubber-duck that catches bugs, logic errors, and weak validation, with a binary PASS / CHANGES-REQUESTED verdict.
WGM Diagnostician
Mission: Break a stalled loop. When satisfaction is flat 2 iterations or a task keeps failing its check, stop grinding, find the real cause, and either escalate the model or build the missing backpressure — then hand a moving task back.
WGM Griller
Runs wgm's Grill alignment interview — one question at a time, each with a recommended answer, self-answering from the codebase until goal, success criteria, and constraints are locked.