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 skills/openshift-online/agent-control-plane/alignnpx skills add openshift-online/agent-control-plane --skill aligngit clone --depth 1 https://github.com/openshift-online/agent-control-planeWhat 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 | $0.00093 | $0.00704 |
| Opus 5 | $0.00046 | $0.00352 |
| Sonnet 5 | $0.00019 | $0.00141 |
| Haiku 4.5 | $0.00009 | $0.00070 |
Grade A, and why
align 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 2d 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.
This is a copy
100% identical to align — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Convention Alignment Check
Measure codebase adherence to documented conventions. Produces a scored report across 5 categories with ~34 checks.
Usage
/align # Full codebase scan
/align backend # Backend checks only
/align frontend # Frontend checks only
/align operator # Operator checks only
/align runner # Runner checks only
/align security # Security checks only
User Input
$ARGUMENTS
How It Works
- Parse scope from
$ARGUMENTS(default: full scan) - Dispatch the
convention-evalagent with the scope- The agent runs in its own context window
- It loads component-level convention docs
- It runs all checks via grep/glob/bash
- It produces a scored report
- Display the report to the user
Dispatching the Agent
Use the Agent tool to dispatch the convention-eval agent:
Agent({
description: "Convention alignment check",
prompt: "You are the convention-eval agent. Read your definition at .claude/agents/convention-eval.md, then run a ${scope} convention alignment check. Scope: ${scope} (one of: full, backend, frontend, operator, runner, security). Load all context files listed in your definition, run the checks, and report findings in the standard output format with scores."
})
If no scope is specified, run all categories.
Report Format
The agent produces a markdown report with:
- Overall weighted score (0-100%)
- Per-category scores (Backend, Frontend, Operator, Runner, Security)
- Pass/fail per check with file:line references
- Failures grouped by severity (Blocker > Critical > Major > Minor)
- Top 3 recommendations for improvement
Categories and Weights
| Category | Checks | Weight | Key concerns |
|---|---|---|---|
| Backend | 8 | 25% | panic, service account misuse, error handling |
| Frontend | 8 | 25% | any types, raw HTML, manual fetch |
| Operator | 7 | 20% | OwnerReferences, SecurityContext, reconciliation |
| Runner | 4 | 10% | async patterns, credential handling |
| Security | 7 | 20% | RBAC, token redaction, input validation |
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.
- 2d ago First seen · 83 lines · 93 tokens per session scan A 16adc2bb86c9
align is a skill published in the GitHub repository openshift-online/agent-control-plane (10 stars, last pushed 4d ago), licensed MIT. It adds 93 tokens to every session and 704 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to align, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
fleet-manager
Use when managing, triaging, restarting, escalating, or summarizing Codewhale Pod runs and workers.
gh-assign-issues
Use to assign GitHub issues to a milestone and/or owners in bulk, verifying each.
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
security-review
Review trust boundaries, auth/authz, injection, secrets, filesystem/network exposure, dependencies, and exploitability without pretending a shallow lint is an audit.
ppt-review
Read this skill only after current officereview structural output and relevant rendered images exist. Do not use source code, a tool success flag, or the first-slide preview as a substitute for deck evidence.