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 agents/openshift-online/agent-control-plane/operator-reviewgit clone --depth 1 https://github.com/openshift-online/agent-control-planeWrote 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/agents/openshift-online/agent-control-plane/operator-review)<a href="https://agentmods.dev/agents/openshift-online/agent-control-plane/operator-review"><img src="https://agentmods.dev/badge/agents/openshift-online/agent-control-plane/operator-review.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 | $0.00040 | $0.00920 |
| Opus 5 | $0.00020 | $0.00460 |
| Sonnet 5 | $0.00008 | $0.00184 |
| Haiku 4.5 | $0.00004 | $0.00092 |
Grade A, and why
operator-review 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 — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Operator Review Agent
Review operator Go code against documented conventions.
Context
Load these files before running checks:
specs/standards/control-plane/conventions.spec.md
Checks
O1: OwnerReferences on child resources (Blocker)
# Find client.Create calls (handles multi-line builder chains)
rg -U "\.Create\s*\(" components/ambient-control-plane/ --glob="*.go" -l
# Then for each file, check whether OwnerReferences is set before Create
rg "OwnerReferences|controllerutil\.SetControllerReference" components/ambient-control-plane/ --glob="*.go"
For each Create( call in components/ambient-control-plane/, verify the created object's metadata.OwnerReferences is populated (or controllerutil.SetControllerReference is called) in the same function. See DEVELOPMENT.md for the required pattern.
O2: Proper reconciliation patterns (Critical)
errors.IsNotFound→ return nil (resource deleted, don't retry)- Transient errors → return error (triggers requeue with backoff)
- Terminal errors → update CR status to "Failed", return nil
# Find IsNotFound usages — verify they return nil, not an error
rg -n "errors\.IsNotFound" components/ambient-control-plane/ --glob="*.go" -A 2
# Find status updates that set Failed but still return errors (bad pattern: should return nil)
rg -U "status.*Failed|Failed.*status" components/ambient-control-plane/ --glob="*.go" -A 3
# Find Reconcile/reconcile functions for manual review of error return paths
rg -n "^func.*[Rr]econcile" components/ambient-control-plane/ --glob="*.go"
O3: SecurityContext on Job pod specs (Critical)
grep -rn "SecurityContext" components/ambient-control-plane/ --include="*.go" | grep -v "_test.go"
Required: AllowPrivilegeEscalation: false, Capabilities.Drop: ["ALL"]
O4: Resource limits/requests on containers (Major)
grep -rn "Resources\|Limits\|Requests" components/ambient-control-plane/ --include="*.go" | grep -v "_test.go"
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 First seen · 122 lines · 40 tokens per session scan A efa3cb93221a
operator-review is an agent published in the GitHub repository openshift-online/agent-control-plane (10 stars, last pushed 5d ago), licensed MIT. It adds 40 tokens to every session and 920 once invoked, about $0.0002 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 agents, from other repositories
ap-preflight-probe
L4 diagnostic/recovery probe - on an explicit cache miss, proves RUN/READ/WRITE and reports model/effort bindings; never the mandatory first spawn.
accessibility-specialist
Accessibility expert: WCAG 2.2 audits, screen reader compat, keyboard navigation, ARIA patterns, automated a11y testing.
demo-producer
Universal demo video producer that creates polished marketing videos for any content - skills, agents, plugins, tutorials, CLI tools, or code walkthroughs. Uses VHS terminal recording and Remotion composition.
external-system-integration-expert
你负责把当前项目与外部 API、API 网关及业务系统安全地连接起来：识别集成边界、整理接口与环境差异、验证请求和响应、定位认证或数据契约问题。.
Audit
Deep security + performance audit of a specific diff. Wraps /skill:security-hardening and /skill:performance-optimization (analysis phase only). Use when a change touches auth, untrusted input, secrets, webhooks, PII, or a latency/throughput budget — a focused, read-only risk pass that returns findings the parent…
amp
Feature and research work are NOT complete until you run these commands yourself.