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 fleet-rungit 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/fleet-run)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/fleet-run"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/fleet-run/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/fleet-run"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/fleet-run.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 | $0.00042 | $0.01544 |
| Opus 5 | $0.00021 | $0.00772 |
| Sonnet 5 | $0.00008 | $0.00309 |
| Haiku 4.5 | $0.00004 | $0.00154 |
Grade A, and why
fleet-run 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 7d 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 — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Your objective is to execute a CocoFleet manifest.
Before proceeding, verify that .cocoplus/ exists.
If not: output "CocoPlus not initialized in this directory. Run $pod init to begin." Then stop.
Parse argument: $fleet run [manifest-path]
If no manifest-path: output "Usage: $fleet run [manifest-path]" Then stop.
Read the manifest file at [manifest-path]. If not found: output "Manifest not found: [manifest-path]" Then stop.
Validate Manifest
Check: instance count ≤ 10. If exceeded: output "WARNING: Fleet has [N] instances, exceeding the 10-instance maximum. Edit manifest to reduce instance count." Then stop.
If mode = "goal_decomposition" or "mode": "goal_decomposition":
- Require a planner role entry that writes
.cocoplus/fleet/[fleet-id]/task-plan.json. - Require each planned task to declare:
idrole:planner,producer, orcriticmodel_tier:smol,regular,smart, orultrafile_scope: array of files or directories owned by the taskdepends_on: array, empty when no predecessor existscritic_required: boolean for producer outputs that need signoff
- Require critic tasks to declare
tool_set: "read_only". A critic that can write the artifact it grades is invalid. - Validate concurrent producer tasks have disjoint
file_scopeentries. If scopes overlap, do not fail the run; rewrite the launch plan so overlapping tasks run sequentially. - A goal-decomposition fleet is complete only after every producer with
critic_required = truehas a dependent critic task with PASS signoff recorded intask-plan.jsonorstate.json.
Check if coco is available (cross-platform: run coco --version and verify exit code 0). If not found: output "ERROR: 'coco' CLI not in PATH. Install Coco and ensure it is accessible before running a fleet." Then stop.
Create Fleet State File
Generate fleet-id: fleet-YYYYMMDD-HHMMSS
Create .cocoplus/fleet/[fleet-id]/.
Write .cocoplus/fleet/[fleet-id]/state.json:
{
"fleet_id": "[fleet-id]",
"manifest_path": "[manifest-path]",
"started_at": "[ISO 8601 timestamp]",
"status": "running",
"mode": "[standard|goal_decomposition]",
"instances": {},
"roles": {
"planner": [],
"producer": [],
"critic": []
}
}
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.
- 7d ago First seen · 128 lines · 42 tokens per session scan A 4f683d1b8403
fleet-run is a skill published in the GitHub repository Snowflake-Labs/cocoplus (720 stars, last pushed 7d ago), licensed MIT. It adds 42 tokens to every session and 1,544 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 2026-09-03.
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.
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…
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.
terraform
Operate Terraform and OpenTofu across the whole infrastructure lifecycle: module structure, state backends and locking, plan/apply workflow, drift detection, remote state, upgrade and refactor flows, and evidence-based diagnostics. Use when running or inspecting terraform plans, applies, state files, imports, or state…
go-to-market
Plan and evaluate go-to-market strategy using positioning, acquisition, growth economics, market-entry, and competitive-response workflows. Do not use for CRM execution, product strategy, legal interpretation, or visual brand design. (April Dunford's positioning, message hierarchy), customer acquisition strategy…
zcfg
Integrate zcfg (Zero Dependency Configuration Utility) into Java applications. Use when adding configuration loading, reading properties files, setting up application configuration, or integrating zcfg into a Java project. Triggers on "zcfg", "add configuration", "load properties", "application configuration with…