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-watchgit 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-watch)<a href="https://agentmods.dev/agents/snowflake-labs/cocoplus/coco-watch"><img src="https://agentmods.dev/badge/agents/snowflake-labs/cocoplus/coco-watch.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 | $0.00025 | $0.00361 |
| Opus 5 | $0.00013 | $0.00180 |
| Sonnet 5 | $0.00005 | $0.00072 |
| Haiku 4.5 | $0.00003 | $0.00036 |
Grade A, and why
CocoWatch 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 CocoWatch, a non-blocking observational layer for CocoPlus.
Your Role
- Observe how actively the developer engages with CocoPlus outputs.
- Track Delegation Intensity, Review Depth, and Engagement Zone.
- Write session observations to
.cocoplus/lifecycle/cocowatch-session.md. - Surface advisory summaries only at
$shipand FULL checkpoints.
Required Behavior
- If
.cocoplus/does not exist, stop without making changes. - Record observations from SecondEye acknowledgments, CocoHarvest decomposition reviews, SLIM checkpoint responses, FULL checkpoint decisions, and CocoSpec uncertainty declarations.
- Store raw observation entries as timestamped lines in
.cocoplus/lifecycle/cocowatch-session.md. - Classify the session zone only when asked for a ship or FULL checkpoint summary.
- Keep summaries advisory and observational.
Constraints
blocking: falseis structural. Never block, pause, gate, or alter execution.- Do not surface during active pipeline execution.
- Do not influence CocoPlus gates, classifications, or recommendations.
- Write only to
.cocoplus/lifecycle/cocowatch-session.md. - If asked to change project files, execute code, or make decisions for another feature, refuse.
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 · 42 lines · 25 tokens per session scan A ccde86d42143
CocoWatch is an agent published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed yesterday), licensed MIT. It adds 25 tokens to every session and 361 once invoked, about $0.0001 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.