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 routinegit 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/routine)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/routine"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/routine/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/routine"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/routine.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 | $0.00044 | $0.00844 |
| Opus 5.5 | $0.00018 | $0.00338 |
| Sonnet 5.5 | $0.00009 | $0.00169 |
| Haiku 4.5 | $0.00004 | $0.00084 |
Grade A, and why
routine 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 1mo 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 — 92 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Use this skill for $routine commands.
Guardrails
- CocoRoutine is opt-in. Read
cocoplus.toml [routine]before scheduling. - If
[routine] enabled = false, report that routines are disabled and stop. - If
[routine] allow_snowflake_tasks = false, list/status operations are allowed, but scheduling must stop before generating or executing TASK SQL. - Routines must not reference local filesystem paths, local MCPs, local environment variables, or developer-specific state.
- CocoPilot may offer scheduling after a successful flow, but it must never auto-schedule.
- Any TASK creation, alteration, or deletion still runs through Safety Gate, RBAC escalation guard, retained proposal rules, and normal Snowflake confirmation behavior.
State
Routines are tracked locally in .cocoplus/routines/registry.json:
{
"version": 1,
"routines": [
{
"name": "daily_health_check",
"flow_id": "flow-health",
"cadence": "daily",
"snowflake_task": "COCOPLUS_DAILY_HEALTH_CHECK",
"status": "active",
"last_run": null,
"next_run": null,
"created_at": "..."
}
]
}
Commands
$routine list
- Verify
.cocoplus/exists. - Read
.cocoplus/routines/registry.json; if absent, showNo scheduled routines. - Display routine name, cadence, status, last run, next run, and Snowflake task name.
$routine schedule <flow> --cadence <cadence>
- Verify
[routine] enabled = trueand[routine] allow_snowflake_tasks = true. - Load the completed flow definition and confirm all required inputs are self-contained.
- Reject flows that reference local paths, local MCPs, local-only credentials, or unsatisfied project-relative files.
- Generate a Snowflake TASK proposal under
.cocoplus/proposals/routine/<timestamp>/. - If the project uses retained proposals, stop and instruct the developer to settle with
$flow settle. - Otherwise, ask for explicit confirmation before executing TASK SQL.
- Update
.cocoplus/routines/registry.jsononly after the Snowflake operation succeeds.
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.
- 1mo ago First seen · 92 lines · 44 tokens per session scan A 87e0c1139325
routine is a skill published in the GitHub repository Snowflake-Labs/cocoplus (724 stars, last pushed 15d ago), licensed MIT. It adds 44 tokens to every session and 844 once invoked, about $0.0002 per session on Opus 5.5. 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
self-host-studio
Install and self-host deco Studio (the open-source control plane) on the user's own infrastructure. Use when the user wants to install, run, self-host, or deploy Studio locally (Docker, Rancher Desktop, kind, minikube) or on Kubernetes (managed or self-managed), or asks to "install Studio", "self-host decocms"…
github-operations
GitHub CLI operations for issues, PRs, milestones, and Projects v2. Covers gh commands, REST API patterns, and automation scripts. Use when managing GitHub issues, PRs, milestones, or Projects with gh.
product-frameworks
Product management frameworks for business cases, market analysis, strategy, prioritization, OKRs/KPIs, personas, requirements, and user research. Use when building ROI projections, competitive analysis, RICE scoring, OKR trees, user personas, PRDs, or usability testing plans.
link-ticket-to-session
Link the current Claude Code session to a ticket (Linear, Jira, GitHub Issues, or GitHub Pull Requests) and cache its title/status in karma. Use when the user explicitly asks to link, attach, associate, or connect this session to a ticket, issue, or PR — e.g. "/link-ticket-to-session ABC-123", "link this session to…
herdr-kit-workflows
Set up and operate Herdr Kit safely: install and configure the plugin and Mastra Code integration, manage Review and Work repository scope, open primary repository workspaces, synchronize managers, materialize or dematerialize managed worktrees, and update Herdr Kit settings or shortcuts.
herdr-manager-query
Query the authoritative global Herdr Review and Work Manager inventory, recommend actionable PR work, and explicitly materialize confirmed remote-only Review Manager records through the plugin's stable public CLI.