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 instruction-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/instruction-rubric)<a href="https://agentmods.dev/skills/snowflake-labs/cocoplus/instruction-rubric"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/instruction-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/instruction-rubric"><img src="https://agentmods.dev/badge/skills/snowflake-labs/cocoplus/instruction-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 | $0.00023 | $0.00388 |
| Opus 5.5 | $0.00009 | $0.00155 |
| Sonnet 5.5 | $0.00005 | $0.00078 |
| Haiku 4.5 | $0.00002 | $0.00039 |
Grade A, and why
instruction-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
Evaluate one queued operation or stage event against the applicable entries in .cocoplus/lifecycle/rubric.json. The rubric is compiled from .cocoplus/lifecycle/cocopod-instructions.md when absent or stale.
Required Contract
- Judge each applicable rule independently and return a probability from 0 through 1, a boolean
violation, and a concise evidence-based reason. - At probability 0.8 or higher, write a pending repair directive naming the rule and source line. The next tool call is blocked until it carries the matching
rubric_repair_id. - At probability 0.5 through less than 0.8, append an operator note without interrupting the session.
- Below 0.5, remain silent. On timeout, unavailable evaluation, or missing rubric data, fail open and append the miss to
lifecycle/audit.md. - Never mutate
cocopod-instructions.mdwhile evaluating it.
Exit Criteria
- Every returned score maps to a rubric rule id.
- Confidence bands produce repair, note, or silent outcomes exactly at the documented thresholds.
- Evaluation failures are audit-visible and non-blocking.
Anti-Rationalization
| Shortcut / Temptation | Why It Fails |
|---|---|
| Return one score for the whole instruction file | Enforcement and calibration operate per rule. |
| Treat uncertainty as a violation | The medium and silent bands exist to preserve calibrated behavior. |
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 · 38 lines · 23 tokens per session scan A 42e618f0046f
instruction-rubric is a skill published in the GitHub repository Snowflake-Labs/cocoplus (724 stars, last pushed 12d ago), licensed MIT. It adds 23 tokens to every session and 388 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
symbi-agent-sdk
Generate boilerplate for wrapping Gemini CLI agents in ORGA governance. Use when building headless agents that run inside Symbiont's CliExecutor or when integrating Gemini CLI with Symbiont's trust stack.
symbi-init
Initialize a Symbiont-governed project. Creates agent definitions, Cedar policies, and configuration files. Use when setting up a new project with AI agent governance or adding Symbiont to an existing project.
symbi-policy
Create, edit, or validate Cedar authorization policies for Symbiont agents. Use when defining access control rules, setting up security policies, or debugging policy evaluation.
symbi-dsl
Parse, validate, and create Symbiont DSL agent definitions. Use when writing new agents, debugging DSL syntax errors, or understanding existing agent definitions.
symbi-verify
Verify MCP tool schemas using SchemaPin cryptographic verification. Use when adding new MCP servers, auditing existing tool integrations, or checking tool integrity.
symbi-audit
Query and analyze Symbiont's cryptographic audit logs. Use when reviewing agent activity, investigating incidents, or preparing compliance reports.