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 UnboundCompute/security-agent-skills --skill auditing-admission-control-policy-gapsgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote 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/unboundcompute/security-agent-skills/auditing-admission-control-policy-gaps)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-admission-control-policy-gaps"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-admission-control-policy-gaps/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/unboundcompute/security-agent-skills/auditing-admission-control-policy-gaps"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-admission-control-policy-gaps.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 | $0.00154 | $0.01954 |
| Opus 5 | $0.00077 | $0.00977 |
| Sonnet 5 | $0.00031 | $0.00391 |
| Haiku 4.5 | $0.00015 | $0.00195 |
Grade A, and why
auditing-admission-control-policy-gaps 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 11d 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 — 136 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing admission control policy gaps: when the gatekeeper waves it through
Admission control is the cluster's gate: every create and update passes through validating and mutating webhooks that are supposed to reject workloads that break policy, privileged pods, unsigned images, over-broad service accounts, host mounts. The gate only protects the cluster if it actually fires on the requests that matter and cannot be skipped. In practice it is riddled with quiet gaps: a webhook configured to fail open so an unreachable backend admits everything, a policy scoped to some namespaces but not the one an attacker targets, an exemption for system workloads that a hostile pod can wear, and a mutating webhook whose output later stages trust without re-validating. A gate with a gap is worse than no gate, because teams believe it is enforcing. You audit this by checking, for each policy, whether it fires on every relevant request and whether anything can bypass it.
When to use
- Admission webhooks or a policy engine are the control keeping non-compliant workloads out of the cluster.
- Webhooks may fail open, be scoped narrowly, carry exemptions, or run in an order that allows a bypass.
- A mutating webhook changes resources that later stages or other policies trust without re-checking.
Scope check
Test admission control only on clusters you own or are authorized to assess, on non-production namespaces. Probing a policy means submitting workloads to a real cluster, so use a non-production namespace and remove any test workload you create. If you can't name the authorization, stop.
The loop
- Establish what each policy must enforce and where first. Name the rules admission control is supposed to guarantee (no privileged pods, only signed images, no host mounts) and the full set of namespaces they must cover. This is the false-positive killer: a policy that fires closed on every relevant request across every namespace, with no usable exemption, is doing its job. Name the intended coverage, then test against it.
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.
- 11d ago First seen · 136 lines · 154 tokens per session scan A 8ce416d97c90
auditing-admission-control-policy-gaps is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 3d ago), licensed MIT. It adds 154 tokens to every session and 1,954 once invoked, about $0.0008 per session on Opus 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
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations and post-launch readiness. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line citations…
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-langgraph
Integrate Arcjet security into a LangGraph Graph API agent using @arcjet/guard — wrap tool() / StructuredTool, wrap ToolNode for unwrapped MCP tools, and read threadid for correlation. Use when asked to add Arcjet to a LangGraph StateGraph / ToolNode agent, rate limit its tools, screen inbound messages, or block…
integrate-arcjet-guard-tanstack-ai
Integrate Arcjet security into a TanStack AI chat() app using @arcjet/guard — put guardMiddleware first on chat({ middleware }) so onBeforeToolCall gates tools, and read a caller-owned id from chat({ context }). Use when asked to add Arcjet to TanStack AI, rate limit its tools, screen inbound messages, or block prompt…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.