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 wangke19/gemini-ai-helpers --skill payload-results-yamlgit 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/skills/wangke19/gemini-ai-helpers/payload-results-yaml)<a href="https://agentmods.dev/skills/wangke19/gemini-ai-helpers/payload-results-yaml"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/payload-results-yaml/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/wangke19/gemini-ai-helpers/payload-results-yaml"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/payload-results-yaml.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 | $0.00028 | $0.02472 |
| Opus 5 | $0.00014 | $0.01236 |
| Sonnet 5 | $0.00006 | $0.00494 |
| Haiku 4.5 | $0.00003 | $0.00247 |
Grade A, and why
Payload Results YAML 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 11d 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.
This is a copy
89% identical to payload-results-yaml — 101 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 196 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Payload Results YAML
This skill defines the schema for the payload-results-{tag}.yaml file and provides the operations for reading and writing it. All skills in the payload triage pipeline must use this skill when interacting with the results file.
When to Use This Skill
Use this skill whenever you need to:
- Create a new results file (during
analyze-payload) - Read candidates or their actions (during
payload-revert,payload-experiment) - Append an action to a candidate (during
stage-payload-reverts,payload-experimental-reverts) - Update an action's status (during
payload-experimental-revertsPhase 2)
File Location
The file is always written to and read from the current working directory:
payload-results-{tag}.yaml
Where {tag} is the full payload tag with colons and slashes replaced by hyphens (e.g., payload-results-4.22.0-0.nightly-2026-02-25-152806.yaml).
Schema
metadata:
payload_tag: "4.22.0-0.nightly-2026-02-25-152806"
version: "4.22"
stream: "nightly"
architecture: "amd64"
release_controller_url: "https://amd64.ocp.releases.ci.openshift.org/..."
analyzed_at: "2026-02-26T10:30:00Z"
failing_jobs:
- job_name: "periodic-ci-...-e2e-aws-ovn"
prow_url: "https://prow.ci.openshift.org/..."
is_aggregated: false
underlying_job_name: ""
failure_type: "test"
root_cause_summary: "OVN gateway mode selection regression"
streak_length: 5
originating_payload_tag: "4.22.0-0.nightly-2026-02-20-150000"
failure_pattern: "F F F F F S S"
- job_name: "periodic-ci-...-e2e-gcp-ovn-techpreview"
prow_url: "https://prow.ci.openshift.org/..."
is_aggregated: false
underlying_job_name: ""
failure_type: "infra"
root_cause_summary: "Pods deleted unexpectedly on build04 cluster"
streak_length: 1
originating_payload_tag: "4.22.0-0.nightly-2026-02-25-152806"
failure_pattern: "F"
candidates:
- pr_url: "https://github.com/openshift/cno/pull/2037"
pr_number: 2037
component: "cluster-network-operator"
title: "Fix OVN gateway mode selection"
confidence_score: 95
rationale: "temporal match + component match + error references code changed"
failing_jobs:
- "periodic-ci-...-e2e-aws-ovn"
actions:
- type: "revert"
status: "staged"
revert_pr_url: "https://github.com/openshift/cno/pull/2038"
revert_pr_state: "open"
result_summary: "Revert PR opened and payload jobs triggered"
jira_key: "TRT-1234"
jira_url: "https://redhat.atlassian.net/browse/TRT-1234"
payload_jobs:
- command: "/payload-job periodic-ci-...-e2e-aws-ovn"
test_url: "https://pr-payload-tests.ci.openshift.org/runs/ci/..."
test_prow_url: "https://prow.ci.openshift.org/view/gs/..."
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.
- 11d ago First seen · 196 lines · 28 tokens per session scan A 94a89fe73fa5
Payload Results YAML is a skill published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 28 tokens to every session and 2,472 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 89% identical to payload-results-yaml, differing in 101 lines, and is treated as a copy.
Other skills, from other repositories
mongodb-query-optimizer
Help with MongoDB query optimization and indexing. Use only when the user asks for optimization or performance: "How do I optimize this query?", "How do I index this?", "Why is this query slow?", "Can you fix my slow queries?", "What are the slow queries on my cluster?", etc. Do not invoke for general MongoDB query…
neo4j-modeling-skill
Design, review, and refactor Neo4j graph data models. Use when choosing node labels vs relationship types vs properties, migrating relational/document schemas to graph, detecting anti-patterns (generic labels, supernodes, missing constraints), designing intermediate nodes for n-ary relationships, enforcing schema with…
lov-bp-outline
A process for turning project information into a source-backed business-plan brief, evidence record, and 12–15-slide outline. A business plan explains how a company works, grows, and makes money.
build-sdf-liquid-glass
Build lightweight SDF/canvas displacement glass with Vaso. Use for responsive refractive cards, no-WebGL fallbacks, many compact surfaces, or explicit SDF requests.
convert-to-devto
Converts Markdown content into the format required for Dev.to publication, ensuring correct YAML frontmatter, headers, liquid tags, and inline formatting. Use when the user asks to format or convert an existing blog post or Markdown file for Dev.to.
lov-app-adapters
An adapter for reading and writing vocabulary lists used by specific apps such as OpenLess and Typeless.