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 analyze-payload-informing-jobsgit 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/analyze-payload-informing-jobs)<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/analyze-payload-informing-jobs"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-payload-informing-jobs/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/analyze-payload-informing-jobs"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/analyze-payload-informing-jobs.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 | $0.00039 | $0.01856 |
| Opus 5.5 | $0.00016 | $0.00742 |
| Sonnet 5.5 | $0.00008 | $0.00371 |
| Haiku 4.5 | $0.00004 | $0.00186 |
Grade A, and why
analyze-payload-informing-jobs 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 — 166 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Analyze payload informing jobs
Analyze informing jobs only after freezing a bounded population of relatively healthy payloads. This workflow produces local recommendations; it does not edit release configuration, change schedules, open issues or PRs, decide payloads, or trigger jobs.
Inputs and defaults
Require release, --architecture, and --stream. Accept natural-language
equivalents and record the effective values. Defaults are a 14-day window ending
at collection start, 10 healthy payloads, 50 inspected payloads, 3 healthy
payloads, 5 distinct runs across 3 payloads per chronic conclusion, 90% blocker
health, 50% poor-job success, --max-recommendations 10, --max-candidates 100,
and --time-budget-minutes 120. Recommendation limits count distinct validated
repair mechanisms and validated retirement candidates; candidate limits count
distinct cohorts started in this invocation. Neither is a quota. The
default --history-release auto-previous uses only the verified immediately
previous release when a newly started release lacks history. Use none to
disable fallback or a release value to select it explicitly.
Reject rates outside [0,1], nonpositive budgets, ambiguous lookback plus
start/end inputs, and non-UTC or reversed boundaries. A deliberately smaller
sample remains provisional. Freeze the end time and never add newer payloads on
restart.
Workspace/output paths are user-selected when supplied. Otherwise the workspace
is ~/tmp/analyze-payload-informing-jobs/<UTC timestamp> and report exports are
fresh timestamped directories inside it.
Resolve bundled paths relative to this SKILL.md, independent of the current
working directory. Python 3.10+ and public HTTPS access are required.
Collect, select, and rank
Read population and ranking, then run:
python3 scripts/collect_payload_jobs.py RELEASE \
--architecture ARCH --stream STREAM --workspace WORK
python3 scripts/rank_jobs.py --workspace WORK
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
- references/investigation-progress.md 6.7 KB
- references/population-and-ranking.md 4.4 KB
- references/recommendation-contract.md 11 KB
- scripts/collect_payload_jobs.py 21 KB runs code
- scripts/export_report.py 37 KB runs code
- scripts/investigation_queue.py 18 KB runs code
- scripts/rank_jobs.py 17 KB runs code
- tests/fixtures/supplied-live-summary.json 998 B
- tests/test_collection.py 13 KB runs code
- tests/test_export.py 26 KB runs code
- tests/test_investigation_queue.py 14 KB runs code
- tests/test_ranking.py 7.1 KB runs code
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 · 166 lines · 39 tokens per session scan A a751d14c88a2
analyze-payload-informing-jobs is a skill published in the GitHub repository openshift-eng/ai-helpers (121 stars, last pushed today), licensed Apache-2.0. It adds 39 tokens to every session and 1,856 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 2026-10-13.
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.…