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/openshift-online/gcp-hcpWrote 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/openshift-online/gcp-hcp/ci-triage)<a href="https://agentmods.dev/commands/openshift-online/gcp-hcp/ci-triage"><img src="https://agentmods.dev/badge/commands/openshift-online/gcp-hcp/ci-triage/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/openshift-online/gcp-hcp/ci-triage"><img src="https://agentmods.dev/badge/commands/openshift-online/gcp-hcp/ci-triage.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 | $0.00016 | $0.00452 |
| Opus 5 | $0.00008 | $0.00226 |
| Sonnet 5 | $0.00003 | $0.00090 |
| Haiku 4.5 | $0.00002 | $0.00045 |
Grade A, and why
ci-triage 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.
What it actually says
Invoke the ci-triage agent using the Task tool with subagent_type="ci-triage".
Pass the following context to the agent:
- PR number: Parse from $ARGUMENTS if provided, otherwise detect from current branch
- Execution mode: If $ARGUMENTS contains "watch", "until green", "until all pass", or "keep trying", use watch mode
What It Does
- Fetches all CI check statuses
- Dynamically classifies checks into Tier 1 (blocking) and Tier 2 (e2e/integration)
- If Tier 1 tests fail (verify, unit, lint, build, security):
- Analyzes logs to find root cause
- Fixes the issues locally
- Commits and pushes the fix
- If only Tier 2 (e2e/integration) tests fail:
- Checks if failures are flaky (infrastructure issues, timeouts)
- If flaky, triggers retests using the repo-appropriate mechanism
- If real failure, reports details for investigation
Execution Modes
Single Pass (default): Run once, fix/retest, report status
Watch Mode: Run continuously until all tests pass
- Polls CI status every 2-3 minutes
- Automatically fixes new failures and retests flaky tests
- Exits when all green or max iterations (10) reached
Examples
/gcp-hcp:ci-triage # Single pass on current branch's PR
/gcp-hcp:ci-triage 7631 # Single pass on PR #7631
/gcp-hcp:ci-triage 7631 watch until green # Watch mode until all pass
/gcp-hcp:ci-triage run until all pass # Watch mode on current PR
$ARGUMENTS
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 · 45 lines · 16 tokens per session scan A f53187564e1c
ci-triage is a command published in the GitHub repository openshift-online/gcp-hcp (2 stars, last pushed yesterday), licensed Apache-2.0. It adds 16 tokens to every session and 452 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 2026-08-31.
Other commands, from other repositories
ci-setup
Setup CI pipeline from scratch. Creates GitHub Actions or GitLab CI configuration with lint, test, build, and deploy stages.
ship
Mechanical pre-deploy gate — tests, build, tree state.
coverage-diff
Run the local diff-coverage check that mirrors CI's Diff coverage required gate.
harness:cicd-fleet
Autonomous CI/CD-remediation orchestrator — triage the red CI/CD-run and flaky-test backlog by cause, fan out worktree-isolated subagents that run the real deflake/heal pipeline, independently verify each fix by artifact and deterministic all-OS CI, and hand back a batch of remediation PRs for one bulk human review.…
ship
Before merging or deploying, run ALL of the following checks. Every gate must pass.
test-setup
Scaffold test framework and CI pipeline.