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/ep-watch)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/ep-watch"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/ep-watch/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/ep-watch"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/ep-watch.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 | $0.00013 | $0.02529 |
| Opus 5 | $0.00006 | $0.01264 |
| Sonnet 5 | $0.00003 | $0.00506 |
| Haiku 4.5 | $0.00001 | $0.00253 |
Grade A, and why
ep-watch scanned grade A with 1 finding 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.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s \ How it starts
The opening of the file, as written. The whole thing — 362 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
olm-team:ep-watch
Synopsis
/olm-team:ep-watch
Description
The olm-team:ep-watch command watches open Enhancement Proposal PRs in the openshift/enhancements repository that are not created by the OLM team but may have impacts on OLM work. This helps the OLM team maintain visibility into what other teams are designing that could affect operator lifecycle management.
The command:
- Fetches open PRs from openshift/enhancements repository
- Filters out PRs created by known OLM team members
- Analyzes PR content for OLM-related topics
- Returns up to 3 most relevant PRs with impact assessment
This is useful for:
- Discovering cross-team dependencies early
- Identifying potential impacts on OLM architecture
- Participating in relevant enhancement discussions
- Staying informed about OpenShift-wide changes affecting operators
Implementation
Step 1: Define OLM-Related Topics
Create a list of topics that could impact OLM:
High Priority Topics (Weight: 10): OLMv1-specific terms that indicate direct relevance:
- olmv1, olm v1
- operator-controller
- catalogd
- rukpak
- ClusterExtension
- boxcutter
Medium Priority Topics (Weight: 5): OLM-specific but broader terms:
- olmv0, olm v0
- operator lifecycle manager, operator-lifecycle-manager
- operator lifecycle
- operator framework
- operator bundle
- operator catalog
- operator registry
- operator hub, operatorhub
Low Priority Topics (Weight: 3): Related terms that must appear in specific context:
- subscription (with "operator")
- csv (with "operator")
- installplan
- catalogsource
Excluded Generic Terms: To reduce false positives, the following generic terms are NOT searched:
- "operator" alone (too broad - matches any operator)
- "marketplace" alone (matches unrelated marketplace mentions)
- "CRD" alone (too generic)
- "webhook" alone (too generic)
Step 2: Identify OLM Team Members
Define list of known OLM team members (GitHub usernames):
OLM_TEAM_MEMBERS = [
"grokspawn",
"joelanford",
"perdasilva",
"tmshort",
"oceanc80",
"dtfranz",
"anik120",
"rashmigottipati",
"pedjak",
"ankitathomas",
"trgeiger",
# Add current OLM team members as needed
]
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 · 362 lines · 13 tokens per session scan A 62a1294084f6
ep-watch is a command published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 13 tokens to every session and 2,529 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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).