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/nareik33l/grane/benchmarknpx skills add Nareik33L/grane --skill benchmarkgit clone --depth 1 https://github.com/Nareik33L/graneWrote 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/nareik33l/grane/benchmark)<a href="https://agentmods.dev/skills/nareik33l/grane/benchmark"><img src="https://agentmods.dev/badge/skills/nareik33l/grane/benchmark.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 | $0.00000 | $0.00789 |
| Opus 5 | $0.00000 | $0.00394 |
| Sonnet 5 | $0.00000 | $0.00158 |
| Haiku 4.5 | $0.00000 | $0.00079 |
Grade A, and why
benchmark 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 today.
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 — 64 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SKILL: Demo shop analytics
Metric definitions for the canonical Grane demo shop (demo/). Read this
before writing analytics SQL against that database.
This file is path B of the A/B/C benchmark: it represents the "good agent + database MCP + well-written SKILL.md" configuration. The definitions below are correct. Whether a model applies them correctly when it writes the joins is what the benchmark measures.
Tables
| table | grain | notes |
|---|---|---|
customers |
one registered account | country, customer_type, plan, email (PII — never query) |
orders |
one order | status, channel, net_amount, created_at, paid_at, settled_at, completed_at, refunded_at, payment_failure_code, discount_code |
order_items |
one line item | 1–3 rows per order |
payments |
one payment attempt | succeeded rows fan out; failed rows have failure_code |
refunds |
one refund | one-to-many from orders |
products |
one product | category |
subscriptions |
one subscription | not the definition of "customer" |
checkout_events |
one event | several per order |
support_tickets |
one ticket | 1–4 per customer |
Relationships: orders.customer_id -> customers.id,
payments.order_id -> orders.id, refunds.order_id -> orders.id,
order_items.order_id -> orders.id, order_items.product_id -> products.id,
checkout_events.order_id -> orders.id,
support_tickets.customer_id -> customers.id,
subscriptions.customer_id -> customers.id.
Metric definitions
Revenue — net amount of successfully completed orders.
SUM(orders.net_amount)whereorders.status = 'completed'- Time dimension:
orders.completed_at. Nevercreated_at,paid_at,settled_at, orrefunded_at. - Unit: GBP. Synonyms: sales, net sales.
Orders — count of completed orders: COUNT(*) where orders.status = 'completed',
timed on completed_at.
AOV — revenue / orders. Both parts use the completed filter. Not AVG(net_amount) over all rows.
What ships with it
6 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- today Changed · -15 lines 8f582656843e
- 4d ago First seen · 79 lines · 0 tokens per session scan A cde947320cba
benchmark is a skill published in the GitHub repository Nareik33L/grane (0 stars, last pushed yesterday), licensed Apache-2.0. It costs nothing until one of its globs matches a file; then it loads 789 tokens. 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 2026-08-31.
Other skills, from other repositories
schema-exploration
Lists tables, describes columns and data types, identifies foreign key relationships, and maps entity relationships in a database. Use when the user asks about database schema, table structure, column types, what tables exist, ERD, foreign keys, or how entities relate.
sdk-design
Doctrine for designing and evolving any SDK Grida ships — TypeScript, Rust, or otherwise. "SDK" here means a surface that crosses a foreign-or-foreign-treated boundary: published packages, separately-versioned consumers, FFI bindings, public-by-design modules. An SDK's job is to refuse; a strict, honest surface…
ha-data-stores
Map of Hope Agent's local data stores and safe read-only query workflow. Use when the user asks where Hope Agent stores data, wants to inspect sessions/messages/memory/logs/background jobs/knowledge indexes/settings, asks the model to query local app data, or debugging requires checking persisted state. Trigger…
supabase
Supabase / PostgREST Row-Level-Security playbook — pull the anon (or leaked servicerole) key out of the frontend JS, map tables from the auto-generated OpenAPI spec, test anonymous RLS READ disclosures (PII/secret leaks), and anonymous RLS WRITE abuse (insert/update/delete — e.g. forging…
dsql
Build with Aurora DSQL — manage schemas, execute queries, handle migrations, diagnose query plans, diagnose cluster performance, load data, and develop applications with a serverless, distributed SQL database. Covers IAM auth, multi-tenant patterns, MySQL-to-DSQL and PostgreSQL-to-DSQL schema conversion, foreign key…
volcengine-rds-postgresql
使用火山引擎 RDS PostgreSQL，帮助用户完成 RDS PostgreSQL 相关的实例管理、数据库操作、账号管理和运维任务，可直接调用 uv run ./scripts/callrdspostgresql.py 脚本获取实时结果。.