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.
npx skills add openshift-eng/ai-helpers --skill chai-presubmit-override-decisionsgit clone --depth 1 https://github.com/openshift-eng/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/skills/openshift-eng/ai-helpers/chai-presubmit-override-decisions)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/chai-presubmit-override-decisions"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/chai-presubmit-override-decisions/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/skills/openshift-eng/ai-helpers/chai-presubmit-override-decisions"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/chai-presubmit-override-decisions.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 | $0.00044 | $0.02395 |
| Opus 5.5 | $0.00018 | $0.00958 |
| Sonnet 5.5 | $0.00009 | $0.00479 |
| Haiku 4.5 | $0.00004 | $0.00239 |
Grade A, and why
chai-presubmit-override-decisions 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 16d 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 — 248 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CHAI Presubmit Override Decisions
Query openshift-gce-devel.ci_analysis_us.chai_presubmit_decision_log to monitor decisions made by the CHAI agent when evaluating PR presubmit failures. The primary goal is understanding the decision breakdown: how many failures are being overridden vs retested vs just reported on, and estimating CI cost savings from overrides.
Follow the foundations skill for cost safety, caching, and execution workflow.
When to Use This Skill
- Monitoring the decision breakdown (override / retest / report_only / no_action_required)
- Estimating CI cost savings from overridden presubmit failures
- Reviewing decisions for a specific PR, repo, or job
- Understanding why the agent made a particular decision (rationale)
- Tracking decision trends over time
- Auditing whether overrides correlate with post-merge regressions
Default Timespan
Use one week unless the user specifies otherwise.
CI Cost Savings
Each overridden presubmit failure saves an estimated $3 per job run in CI costs (cloud compute for the retest that was avoided). When reporting override counts, always calculate and display the estimated savings:
estimated_savings = override_count * $3.00
Table
ci_analysis_us.chai_presubmit_decision_log
Project: openshift-gce-devel
Each row represents one decision the CHAI agent made about a PR presubmit failure.
| Column | Type | Notes |
|---|---|---|
| logged_at | TIMESTAMP | When the record was appended (UTC) |
| persona | STRING | The persona that appended the record |
| session_id | STRING | The conversation session ID |
| repo | STRING | The PR's repository |
| pr_number | INTEGER | The PR number |
| head_sha | STRING | The live PR HEAD SHA the decision was made against |
| run_sha | STRING | The SHA the failed run tested, when known |
| revision_match | BOOLEAN | Whether the failed run tested the live PR HEAD SHA |
| status_context | STRING | Full GitHub status context (e.g. ci/prow/e2e-gcp-ovn-upgrade) |
| prow_job_name | STRING | Full Prow job name |
| prow_build_id | STRING | Prow build ID of the failed run |
| prow_job_url | STRING | Prow job URL of the failed run |
| run_finished_at | TIMESTAMP | When the failed run finished |
| decision | STRING | The action taken: override, retest, report_only, no_action_required |
| job_classification | STRING | Whether the job is an override-eligible long-running e2e or integration job |
| tests_executed | BOOLEAN | Whether the failed run executed tests |
| failing_tests | STRING (REPEATED) | The failing test names |
| job_pass_rate | FLOAT | Fleet-wide pass rate for this job (0-100) |
| linked_bugs | STRING (REPEATED) | Jira bugs linked to failing tests (e.g. OCPBUGS-12345) |
| pr_overlap | STRING | The PR's overlap with the failing test or tested surface |
| rationale | STRING | Why this decision was made, in a short paragraph |
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.
- 16d ago First seen · 248 lines · 44 tokens per session scan A e54563dfa79a
chai-presubmit-override-decisions is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 44 tokens to every session and 2,395 once invoked, about $0.0002 per session on Opus 5.5. 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 2026-10-06.
Other skills, from other repositories
chinese-git-workflow
A reference for configuring Git with Chinese code-hosting services such as Gitee, Coding.net, GitLab China, and CNB, including SSH, HTTPS, credentials, CI, and repository mirroring.
atmos-profiles
Atmos profiles: profile directories, --profile and ATMOSPROFILE activation, profile merge behavior, environment switching, and routing profile-specific auth/toolchain/config overrides.
webhook-management
Configure and validate CCAM webhook targets across supported chat, incident, automation, and generic providers. Use when listing provider requirements, creating or updating a target, scoping it to alert rules, sending a test notification, reviewing delivery history, or deleting a target.
managing-github-actions-secrets
Creates and updates GitHub Actions secrets for PostHog workflows. Use when adding a new CI secret, rotating an existing secret, wiring a workflow to an API token, package registry credential, deploy key, or any value referenced via ${{ secrets. }} in .github/workflows/.
monorepo-management
Master monorepo management with Turborepo, Nx, and pnpm workspaces to build efficient, scalable multi-package repositories with optimized builds and dependency management. Use when setting up monorepos, optimizing builds, or managing shared dependencies.
deployment-engineer
Expert deployment engineer specializing in modern CI/CD pipelines, GitOps workflows, and advanced deployment automation. Masters GitHub Actions, ArgoCD/Flux, progressive delivery, container security, and platform engineering. Handles zero-downtime deployments, security scanning, and developer experience optimization.…