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.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersWrote 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/commands/wangke19/gemini-ai-helpers/diagnose)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/diagnose"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/diagnose/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/commands/wangke19/gemini-ai-helpers/diagnose"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/diagnose.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 | $0.00011 | $0.03284 |
| Opus 5 | $0.00005 | $0.01642 |
| Sonnet 5 | $0.00002 | $0.00657 |
| Haiku 4.5 | $0.00001 | $0.00328 |
Grade A, and why
diagnose 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 5d 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 — 411 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
olm:diagnose
Synopsis
/olm:diagnose [operator-name] [namespace] [--fix] [--cluster]
Description
The olm:diagnose command diagnoses common OLM and operator issues, including orphaned CRDs, stuck namespaces, failed installations, and catalog source problems. It can optionally attempt to fix detected issues automatically.
This command helps you:
- Detect and clean up orphaned CRDs from deleted operators
- Fix namespaces stuck in Terminating state
- Identify and resolve failed operator installations
- Detect conflicting OperatorGroups
- Check catalog source health
- Identify resources preventing clean uninstallation
- Generate comprehensive troubleshooting reports
Implementation
The command performs the following steps:
-
Parse Arguments:
$1: Operator name (optional) - Specific operator to diagnose$2: Namespace (optional) - Specific namespace to check$3+: Flags (optional):--fix: Automatically attempt to fix detected issues (requires confirmation)--cluster: Run cluster-wide diagnostics (catalog sources, global CRDs, etc.)
-
Prerequisites Check:
- Verify
ocCLI is installed:which oc - Verify cluster access:
oc whoami - Check if user has cluster-admin or sufficient privileges
- Warn if running without
--fixflag (dry-run mode)
- Verify
-
Determine Scope:
- Operator-specific: If operator name provided, focus on that operator
- Namespace-specific: If namespace provided, check all operators in that namespace
- Cluster-wide: If
--clusterflag or no arguments, check entire cluster
-
Scan for Orphaned CRDs:
- Get all CRDs in the cluster:
oc get crd -o json - For each CRD, check if there's a corresponding operator:
- Look for CSVs that own this CRD
- Look for active Subscriptions related to this CRD
- Identify orphaned CRDs (no owning operator found):
# Find CRDs without active operators # This is a simplified check - actual implementation should verify operator ownership oc get crd -o json | jq -r '.items[] | select(.metadata.annotations["operators.coreos.com/owner"] // "" | length == 0) | .metadata.name' - Check if CRs exist for orphaned CRDs:
oc get <crd-kind> --all-namespaces --ignore-not-found - Report findings:
⚠️ Orphaned CRDs Detected The following CRDs have no active operator: - certificates.cert-manager.io (3 CR instances in 2 namespaces) - issuers.cert-manager.io (5 CR instances in 3 namespaces) These CRDs may be leftovers from uninstalled operators. [If --fix flag:] Do you want to delete these CRDs and their CRs? (yes/no) WARNING: This will delete all custom resources of these types!
- Get all CRDs in the cluster:
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.
- 5d ago First seen · 411 lines · 11 tokens per session scan A f7c43ce8f0a8
diagnose is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 11 tokens to every session and 3,284 once invoked, about $0.0001 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 2026-09-03.
Other commands, from other repositories
audit
Run a structured codebase audit. Maps the architecture, assesses health (compliance, tests, docs), performs deep analysis (security, performance, code quality), and synthesizes a prioritized roadmap. Outputs land under docs/audit/ in this project. Phases 0-3 with human checkpoints between each phase. Use /audit-quick…
wtfp:report-bug
Collect a reproducible bug report and publish it only after explicit user approval.
fix
Diagnose and fix bugs, errors, and issues in code.
bug-report
Structured bug-fix protocol per docs/methodology/bug-protocol.md. Use when asked to '/bug-report', 'I found a bug', 'something is broken', 'fix this bug', 'report a bug', 'this is broken'.
bmad-review-adversarial-general
Deprecated — forwards to bmad-review.
bmad-review-edge-case-hunter
Deprecated — forwards to bmad-review.