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 thepartly/pgroles --skill pgroles-operatorgit clone --depth 1 https://github.com/thepartly/pgrolesWrote 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/thepartly/pgroles/pgroles-operator)<a href="https://agentmods.dev/skills/thepartly/pgroles/pgroles-operator"><img src="https://agentmods.dev/badge/skills/thepartly/pgroles/pgroles-operator/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/thepartly/pgroles/pgroles-operator"><img src="https://agentmods.dev/badge/skills/thepartly/pgroles/pgroles-operator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 1 finding, up to medium
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- medium Excessive Agency · line 156 Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
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 | $0.00056 | $0.04395 |
| Opus 5.5 | $0.00022 | $0.01758 |
| Sonnet 5.5 | $0.00011 | $0.00879 |
| Haiku 4.5 | $0.00006 | $0.00439 |
Grade A, and why
pgroles-operator 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 3d 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 — 409 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Pgroles Operator
Use the deployed chart and CRD as the schema authority. Do not copy fields from newer upstream documentation into an older cluster.
Load the pgroles-policy skill as well when changing roles, profiles, grants,
memberships, ownership, default privileges, or retirements.
Install or upgrade with the Helm instructions for the target release. Always inspect chart values and rendered resources before applying an upgrade:
helm show values oci://ghcr.io/thepartly/charts/pgroles-operator \
--version <version>
helm template pgroles-operator \
oci://ghcr.io/thepartly/charts/pgroles-operator \
--version <version> --namespace pgroles-system --include-crds \
--values values.yaml > pgroles-operator-rendered.yaml
Helm does not upgrade objects shipped in a chart's crds/ directory. Apply the
version-matched CRDs explicitly before upgrading the controller:
set -euo pipefail
helm show crds oci://ghcr.io/thepartly/charts/pgroles-operator \
--version <version> > pgroles-operator-crds.yaml
test -s pgroles-operator-crds.yaml
kubectl apply --server-side -f pgroles-operator-crds.yaml
helm upgrade --install pgroles-operator \
oci://ghcr.io/thepartly/charts/pgroles-operator \
--version <version> --namespace pgroles-system --create-namespace \
--values values.yaml
Review the rendered CRD and workload diff before applying it. The API is
v1alpha1 and has no conversion webhook; check release notes for compatibility
and rollback implications.
Execution And Reconciliation
Two independent controls determine behavior:
spec.mode: observecomputes and publishes a filtered plan without executing PostgreSQL SQL.spec.mode: applymay execute the filtered plan, subject tospec.approval.spec.reconciliation_modeselectsadditive,adopt, orauthoritativefiltering. See the policy skill before changing it.
Treat observe to apply, approval changes, and stronger reconciliation modes as
operational database migrations. Review generated SQL and replacement access
before enabling execution.
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.
- 3d ago Changed · +20 lines 946692ae242b
- 6d ago Changed · +40 lines 3b3619919a3b
- 1mo ago Changed 907b675e81ba
- 1mo ago Changed · +24 lines b8f000dfd7da
- 1mo ago Changed · +16 lines 61fb8fcfa73b
- 1mo ago First seen · 309 lines · 56 tokens per session scan A 0beab5c9df45
pgroles-operator is a skill published in the GitHub repository thepartly/pgroles (26 stars, last pushed 3d ago), licensed MIT. It adds 56 tokens to every session and 4,395 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 2026-09-05.
Other skills, from other repositories
cloud-sql-basics
This file generates or explains Cloud SQL resources. Use this file when the user asks to create a Cloud SQL instance or database for MySQL, PostgreSQL, or SQL Server. Cloud SQL manages third-party MySQL, PostgreSQL, and SQL Server instances as resources in Cloud SQL. For example, when Cloud SQL creates an open-source…
moai-platform-database-cloud
Cloud database platform specialist covering Neon (serverless PostgreSQL), Supabase (PostgreSQL 16 with real-time), and Firebase Firestore (NoSQL with offline sync). Use when choosing or setting up cloud databases.
aws-rds
Manage Amazon RDS for fully managed relational databases. Provision MySQL, PostgreSQL, and Aurora instances with automated backups and patching. Configure read replicas for scaling, snapshots for recovery, and Aurora Serverless for variable workloads.
backup-recovery
Design and verify backups and restoration for owned databases, files and application state. Use when preparing recovery, migrating data or testing backups; protect the source and prove restore into an isolated destination before calling recovery ready.
blueprint-from-collection-import
Move the copied collection's records into Postgres and the files they point at into Storage, proven on a freshly reset local database.
aws-rds-spring-boot-integration
Provides patterns to configure AWS RDS (Aurora, MySQL, PostgreSQL) with Spring Boot applications. Configures HikariCP connection pools, implements read/write splitting, sets up IAM database authentication, enables SSL connections, and integrates with AWS Secrets Manager. Use when setting up RDS connections in Spring…