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 skills/snowflake-labs/cocoplus/observernpx skills add Snowflake-Labs/cocoplus --skill observergit 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/observer)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/observer"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/observer.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 5.1 | $0.00021 | $0.00549 |
| Opus 5 | $0.00010 | $0.00275 |
| Sonnet 5 | $0.00004 | $0.00110 |
| Haiku 4.5 | $0.00002 | $0.00055 |
Grade A, and why
observer 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 2d 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 — 53 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to observe CocoPlus skills without modifying them.
Behavior
CocoObserver is eyes-only. It reads skill files, hooks, docs, and validation output to identify:
- improvement opportunities,
- simplification opportunities,
- cross-cutting principles that apply to many skills,
- open-source/internal boundary risks.
It never edits files. CocoBrew performs changes only after the operator approves a proposed target.
Detection Signals
- Skill discovery: when three or more session signals match a skill category, append a discovery record instead of surfacing immediate advice. CocoPilot may later choose one discovery to present.
- Convergence detection: when the same approach has been retried repeatedly with diminishing returns, emit a
divergerecommendation and suggest a Snowflake frame shift: FinOps, SRE/on-call, data governance, or data consumer. - Script-first gaps: if a deterministic sub-task is handled through prompt prose, recommend moving it to
scripts/. - Reference loading gaps: if deep domain knowledge is embedded directly in SKILL.md, recommend moving it to
references/and loading on demand. - Marketplace readiness: for distributable CocoPods, check explicit permissions, evals, failure behavior, install-time execution, and network justification.
Outputs
.cocoplus/skills/observations.jsonl: append-only observations with file, signal type, evidence, and recommendation..cocoplus/skills/cross-cutting-principles.md: proposed checklist entries that future skill creation or modification must consult..cocoplus/session/discoveries.jsonl: skill-match and convergence signals consumed by CocoPilot.
Exit Criteria
- Every observation cites exact files read.
- Simplification signals are treated as first-class findings.
- Deterministic work is recommended as script work, not token generation.
- Convergence findings recommend isolated divergence rather than another same-frame retry.
- Public skills do not receive private implementation details.
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.
- 2d ago First seen · 53 lines · 21 tokens per session scan A 7d905f106511
observer is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 2d ago), licensed MIT. It adds 21 tokens to every session and 549 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 2026-09-03.
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.
implementation-final-review
Perform the repository's risk-tiered independent final review before implementation completion. Use only when explicitly invoked or when repository instructions require it after behavior-impacting implementation work; audit the complete task diff, supported contracts, lifecycle and security boundaries, complexity, and…
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…
initialize
First-run setup interview for a Danus deployment. Run it on the FIRST session, whenever runtime/.danus-initialized is absent or OPERATOR.md is still the blank template, or when the operator asks to set up / initialize / onboard / re-configure. It greets the operator, explains Danus, asks the critical choice (codex…
playground-msw-tests
REQUIRED and PRIMARY testing approach for packages/playground and packages/playground-ui. Triggers on: adding or modifying hooks, pages, route components, data-fetching code, React Query interactions, or any test work in these packages. Generates Vitest tests that drive the real @mastra/client-js + React Query stack…
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.