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/approve)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/approve"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/approve/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/approve"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/approve.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 | $0.00009 | $0.02356 |
| Opus 5 | $0.00005 | $0.01178 |
| Sonnet 5 | $0.00002 | $0.00471 |
| Haiku 4.5 | $0.00001 | $0.00236 |
Grade A, and why
approve 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 9d 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 — 306 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
olm:approve
Synopsis
/olm:approve <operator-name> [namespace] [--all]
Description
The olm:approve command approves pending InstallPlans for operators with manual approval mode. This is required for operators that have installPlanApproval: Manual in their Subscription to proceed with installation or upgrades.
This command helps you:
- Approve operator installations that are waiting for manual approval
- Approve operator upgrades
- Review what will be installed/upgraded before approval
- Batch approve multiple pending InstallPlans
Implementation
The command performs the following steps:
-
Parse Arguments:
$1: Operator name (required) - Name of the operator$2: Namespace (optional) - Namespace where operator is installed- If not provided, searches for the operator across all namespaces
$3: Flag (optional):--all: Approve all pending InstallPlans in the namespace
-
Prerequisites Check:
- Verify
ocCLI is installed:which oc - Verify cluster access:
oc whoami - Check if user has sufficient privileges
- Verify
-
Locate Operator:
- If namespace provided, verify operator exists:
oc get subscription {operator-name} -n {namespace} --ignore-not-found - If no namespace provided, search across all namespaces:
oc get subscription --all-namespaces -o json | jq -r '.items[] | select(.spec.name=="{operator-name}") | .metadata.namespace' - If not found, display error with suggestions
- If namespace provided, verify operator exists:
-
Check Subscription Approval Mode:
- Get Subscription approval mode:
oc get subscription {operator-name} -n {namespace} -o jsonpath='{.spec.installPlanApproval}' - If mode is "Automatic", display informational message:
ℹ️ Operator '{operator-name}' has automatic approval enabled. InstallPlans are approved automatically and don't require manual intervention. Current Subscription approval mode: Automatic To switch to manual approval mode: oc patch subscription {operator-name} -n {namespace} \ --type merge --patch '{"spec":{"installPlanApproval":"Manual"}}' - Exit if automatic (no approval needed)
- Get Subscription approval mode:
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.
- 9d ago First seen · 306 lines · 9 tokens per session scan A fb457e5e1960
approve is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 9 tokens to every session and 2,356 once invoked, about $0.0000 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
projects
Provides tools for creating and managing your Supabase projects.
session-list
List recent sessions from the project ledger and offer to view one.
7a_stakeholder_comms
Generate stakeholder-facing communications: release notes, demo scripts, and change briefs.
convert-to-plan
Convert planning artifacts (lite-plan, workflow session, markdown) to issue solutions.
execute
Execute queue with DAG-based parallel orchestration (one commit per solution).
queue
Form execution queue from bound solutions using issue-queue-agent (solution-level).