Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpersnpx agentmods add commands/wangke19/gemini-ai-helpers/health-check-regressionsWrote 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/health-check-regressions)<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/health-check-regressions"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/health-check-regressions/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/health-check-regressions"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/health-check-regressions.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 | $0.03221 |
| Opus 5 | $0.00006 | $0.01611 |
| Sonnet 5 | $0.00003 | $0.00644 |
| Haiku 4.5 | $0.00001 | $0.00322 |
Grade A, and why
health-check-regressions 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 — 321 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Name
teams:health-check-regressions
Synopsis
/teams:health-check-regressions <release> [--components comp1 comp2 ...] [--start YYYY-MM-DD] [--end YYYY-MM-DD]
/teams:health-check-regressions <release> --team <team-name> [--start YYYY-MM-DD] [--end YYYY-MM-DD]
Description
The teams:health-check-regressions command queries regression data for a specified OpenShift release and generates summary statistics. It leverages the list-regressions command to fetch raw regression data and then presents counts, percentages, and timing metrics to help understand regression trends at a glance.
By default, the command analyzes:
- All regressions within the release development window
- Both open and closed regressions
- Triage coverage and timing metrics
- Per-component breakdowns
This command is useful for:
- Getting a quick count of regressions in a release
- Analyzing regression distribution by component or team
- Tracking triage coverage and response times
- Generating summary reports for regression management
- Monitoring regression resolution speed by component or team
- Comparing regression metrics across different components
- Understanding open vs closed regression breakdown
- Getting team-level regression summaries across all team components
Implementation
-
Verify Prerequisites: Check that Python 3 is installed
- Run:
python3 --version - Verify version 3.6 or later is available
- Run:
-
Parse Arguments: Extract release version and optional filters from arguments
- Release format: "X.Y" (e.g., "4.17", "4.21")
- Optional filters:
--components: Space-separated list of component search strings (fuzzy match)--team: Team name (looks up all components for that team)--start: Start date for filtering (YYYY-MM-DD)--end: End date for filtering (YYYY-MM-DD)
- Note:
--componentsand--teamare mutually exclusive
-
Resolve Component Names: Use fuzzy matching to find actual component names, or look up by team
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 · 321 lines · 13 tokens per session scan A 659826ea9748
health-check-regressions 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 3,221 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
red-team
description: "Red team AI system for vulnerabilities".
integration-test-cycle
Self-iterating integration test workflow with codebase exploration, test development, autonomous test-fix cycles, and reflection-driven strategy adjustment.
test
Write tests before implementation using Red-Green-Refactor.
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.