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 openshift-online/agent-control-plane --skill acp-review-guidancegit 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/skills/openshift-online/agent-control-plane/acp-review-guidance)<a href="https://agentmods.dev/skills/openshift-online/agent-control-plane/acp-review-guidance"><img src="https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/acp-review-guidance/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/openshift-online/agent-control-plane/acp-review-guidance"><img src="https://agentmods.dev/badge/skills/openshift-online/agent-control-plane/acp-review-guidance.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 | $0.00048 | $0.00705 |
| Opus 5 | $0.00024 | $0.00352 |
| Sonnet 5 | $0.00010 | $0.00141 |
| Haiku 4.5 | $0.00005 | $0.00071 |
Grade A, and why
acp-review-guidance 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 — 69 lines — stays where its author put it; the contents beside it link to each section on GitHub.
ACP Review Guidance
Apply these standards in addition to the fleet pr-review skill when reviewing PRs in this repository. The pr-review skill defines the review process (summarize, worktree, context, analyze, report). This skill defines what to check during Steps 3 and 4 of that process.
Step 3 Supplement: Mandatory Context Files
Before analyzing any PR in this repo, load all of the following:
CLAUDE.mdspecs/standards/security/security.spec.mdspecs/standards/control-plane/conventions.spec.md
Step 4 Supplement: ACP Review Checklists
Go Backend
- All user operations use
GetK8sClientsForRequest(c), never service account fallback - No tokens in logs — use
len(token)for diagnostics - Type-safe unstructured access (
unstructured.NestedMap, not direct assertions) - No
panic()in production code — returnfmt.Errorfwith context - Errors wrapped:
fmt.Errorf("context: %w", err) -
errors.IsNotFoundhandled for 404 scenarios - OwnerReferences set on child resources (Jobs, Secrets, PVCs)
React/TypeScript Frontend
- Zero
anytypes — use proper types,unknown, or generic constraints - Shadcn UI components only — no custom buttons, inputs, dialogs
- React Query for all data operations — no manual
fetch()in components -
typepreferred overinterface - Single-use components colocated with their page
- Loading and error states handled
- Query keys include all relevant parameters
Security (All Components)
- RBAC check performed before resource access
- No tokens or secrets in logs or error messages
- Input validated (K8s DNS labels, URL parsing)
- Log injection prevented — no raw newlines in logged user input
- Generic error messages to users, detailed logs server-side
- Container SecurityContext:
AllowPrivilegeEscalation: false,Drop: ALL
General
- No
panic()in production Go code - No
anytypes in frontend TypeScript - Feature flags gate new features (Unleash)
- OwnerReferences on all new K8s child resources
- New API endpoints have corresponding frontend proxy routes
- PostgreSQL for persistent storage (not files)
What ships with it
1 file 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.
- 11d ago First seen · 69 lines · 48 tokens per session scan A 60994d7c0b10
acp-review-guidance is a skill published in the GitHub repository openshift-online/agent-control-plane (11 stars, last pushed yesterday), licensed MIT. It adds 48 tokens to every session and 705 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 skills, from other repositories
gh-find-prs
Survey open Codewhale PRs and triage each for mergeability and disposition against the real landing branch.
review
Read-only correctness review with actionable findings first, tight file/line evidence, severity, and a concise residual-risk summary.
improve
Autonomous quality improvement loop. Scores a target against a rubric, selects the highest-leverage axis, attacks it, verifies, documents, and loops. No pre-planning between iterations — each loop re-scores from scratch.
triage
GitHub issue and PR investigator. Pulls open issues/PRs, classifies them, searches the codebase for root cause or reviews contributed code, proposes fixes with file:line references, and optionally implements fixes. Use for investigating GitHub issues and reviewing PRs; do NOT use for general code review unrelated to…
code-review-patterns
Multi-dimensional code assessment across security, quality, performance, and maintainability with confidence-gated reporting (>=80%) and Router Contract generation.
code-review-pipeline
Multi-dimensional code review across correctness, security, performance, and maintainability with confidence-gated reporting and remediation loops.