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 controlplane-com/ai-plugin --skill access-controlgit clone --depth 1 https://github.com/controlplane-com/ai-pluginWrote 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/controlplane-com/ai-plugin/access-control)<a href="https://agentmods.dev/skills/controlplane-com/ai-plugin/access-control"><img src="https://agentmods.dev/badge/skills/controlplane-com/ai-plugin/access-control/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/controlplane-com/ai-plugin/access-control"><img src="https://agentmods.dev/badge/skills/controlplane-com/ai-plugin/access-control.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector pass
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 | $0.00052 | $0.02036 |
| Opus 5.5 | $0.00021 | $0.00814 |
| Sonnet 5.5 | $0.00010 | $0.00407 |
| Haiku 4.5 | $0.00005 | $0.00204 |
Grade A, and why
access-control 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 17d 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 — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Access Control & Policies — Primary Skill
Tool availability:
create_group,edit_group,create_service_account,update_service_account,add_key_to_service_account, andinvite_user_to_orgneed?toolsets=full; reconnect with it or use the CLI.
A policy targets one resource kind and binds permissions to principals (users, groups, service accounts, workload identities). The common failure is a policy that exists but grants nothing — a wrong targetKind, permission name, or principal link fails with no error — so read the policy back after writing.
The model
| Layer | Scope | Controls |
|---|---|---|
| Billing-account roles | account-wide (set on the billing account, separate from org policies) | billing_admin, billing_viewer, org_creator — none grant org-resource access |
| Org policies | per resource kind | all day-to-day access |
A caller is allowed an action when some policy on the resource's kind has a binding that lists that action (or a permission implying it) and names the caller — or a group the caller is in.
Policy anatomy
A policy = one targetKind + a target scope + bindings.
kind: policy
name: app-secret-access
targetKind: secret # exactly one resource kind
targetLinks: # OR `target: all` OR `targetQuery:` (pick one)
- //secret/database-url
bindings: # ≤ 50
- permissions: [reveal, use]
principalLinks: # 1–200
- //gvc/production/identity/app-identity
Limits: bindings ≤ 50; principalLinks 1–200 per binding; targetLinks ≤ 200. origin is read-only — default (yours) or builtin (locked; see Built-ins).
Target scope (pick one): target: all (org-wide roles) · targetLinks (specific resources) · targetQuery (tag query — see query-spec).
Valid target kinds: the targetKind enum accepts all 33 resource kinds, but only the 20 kinds with permission schemas (the ones get_permissions accepts) are meaningful targets: workload, secret, gvc, identity, image, org, policy, group, serviceaccount, user, volumeset, domain, location, ipset, mk8s, cloudaccount, agent, auditctx, quota, task.
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.
- 17d ago Changed · -41 lines 1b3730ef369f
- 1mo ago First seen · 155 lines · 52 tokens per session scan A d9559a23afe2
access-control is a skill published in the GitHub repository controlplane-com/ai-plugin (11 stars, last pushed 3d ago), licensed MIT. It adds 52 tokens to every session and 2,036 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 2026-08-31.
Other skills, from other repositories
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
senior-java
World-class Java and Spring Boot development skill for enterprise applications, microservices, and cloud-native systems. Expertise in Spring Framework, Spring Boot 3.x, Spring Cloud, JPA/Hibernate, and reactive programming with WebFlux. Includes project scaffolding, dependency management, security implementation, and…
ak-cloud-deploy
Deploy an Agent Kernel project to AWS, Azure, or GCP using Terraform modules, or to any Kubernetes cluster (on-prem, baremetal, EKS) using the official Helm chart. Supports serverless and containerized modes for all three clouds. AWS supports execution modes (restsync, restasync, async, stream), queue-based scalable…
ak-build
Add tools, agents, and handoffs to an existing Agent Kernel project. This skill guides you through reading the current project, understanding its framework and structure, then making context-aware additions — new tools, new agents, agent-to-agent handoffs, and Module wiring. The workhorse skill for iterative agent…
ak-add-integration
Add a messaging platform integration to an existing Agent Kernel project. This skill guides you through adding Slack, WhatsApp, Messenger, Instagram, Telegram, Teams, or Gmail integration by generating configuration, updating dependencies, and setting up webhook handlers. Designed for users extending their agents.
ak-init
Scaffold a new Agent Kernel project from scratch. This skill guides you through choosing an agent framework, defining tools, selecting a deployment target, and generating a complete project with all necessary files. Designed for users who want to build a new AI agent using the Agent Kernel library.