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 calibrate-rubricgit 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/calibrate-rubric)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/calibrate-rubric"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/calibrate-rubric/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/calibrate-rubric"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/calibrate-rubric.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 | $0.00022 | $0.00233 |
| Opus 5.5 | $0.00009 | $0.00093 |
| Sonnet 5.5 | $0.00004 | $0.00047 |
| Haiku 4.5 | $0.00002 | $0.00023 |
Grade A, and why
calibrate-rubric 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 16d 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
Objective
Implement $cocopod calibrate-rubric by reading recent rubric result history and updating each rubric entry's calibration metadata. A rule whose evaluated samples all score at or below 0.4 is marked never_fires; a rule with no samples is marked insufficient_evidence.
Exit Criteria
- Every rubric entry has sample count, maximum observed probability, status, and calibration timestamp.
- Calibration does not rewrite instruction text.
Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|---|---|
| Mark an unsampled rule as never firing | No evidence is different from low-scoring evidence. |
| Use wall-clock age as the signal | Calibration is based on observed operations. |
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.
- 16d ago First seen · 29 lines · 22 tokens per session scan A 3b6681a412f5
calibrate-rubric is a skill published in the GitHub repository Snowflake-Labs/cocoplus (724 stars, last pushed 12d ago), licensed MIT. It adds 22 tokens to every session and 233 once invoked, about $0.0001 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 2026-10-01.
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.
langgraph
LangGraph 1.x (LTS) Python workflow patterns for state management, delta channels, resilience (node timeouts, error handlers, graceful drain), routing, parallel execution, supervisor-worker, tool calling, checkpointing, human-in-loop, streaming (v2 format), subgraphs, and functional API. Use when building LangGraph…
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…
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…
cncf-landscape
Use this skill when discovering and comparing cloud-native technologies from the CNCF Landscape for an architecture or engineering decision. Query the live public Landscape API, filter candidates by capability, category, maturity, license, and repository signals, then produce an evidence-backed shortlist with…
go-to-market
Plan and evaluate go-to-market strategy using positioning, acquisition, growth economics, market-entry, competitive-response, and governed agent-assisted acquisition experiments. Use for ICP, messaging, channel, CAC/LTV, beachhead, or automated-GTM strategy decisions. Do not use for campaign execution, CRM mutations…