payload-experimental-reverts

payload-experimental-reverts is a skill for Claude Code, Codex from openshift-eng/ai-helpers. It costs 23 tokens per session (2,346 once invoked), scanned A, original, Apache-2.0.

A workflow for testing uncertain payload-failure causes by opening draft pull requests that undo suspected changes and running payload jobs. A payload is a tested batch of software changes prepared for release.

In plain words
What is it for?
It helps test medium-confidence candidates, trigger continuous-integration jobs, wait for results, and record the outcome in the triage file.
Why use it?
It provides evidence about whether a particular pull request caused a failure when static analysis alone is inconclusive.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one. Also seen: mentions subagents.

Part of the ci plugin — 34 skills, 21 commands, 2 agents shipped together

Good fit It helps test medium-confidence candidates, trigger continuous-integration jobs, wait for results, and record the outcome in the triage file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/openshift-eng/ai-helpers/payload-experimental-reverts
Install

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.

Any agent
npx skills add openshift-eng/ai-helpers --skill payload-experimental-reverts
Clone the repo
git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code, Codex.

Or install ci, the plugin that ships this one along with the rest of its 34 skills, 21 commands, 2 agents.

Wrote 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.

agentmods badge for payload-experimental-reverts

README.md
[![agentmods](https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/payload-experimental-reverts/github.svg)](https://agentmods.dev/skills/openshift-eng/ai-helpers/payload-experimental-reverts)
Your own site
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/payload-experimental-reverts"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/payload-experimental-reverts/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.

agentmods 80×15 button for payload-experimental-reverts

Your own site · 80×15
<a href="https://agentmods.dev/skills/openshift-eng/ai-helpers/payload-experimental-reverts"><img src="https://agentmods.dev/badge/skills/openshift-eng/ai-helpers/payload-experimental-reverts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,346 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits
  • NVIDIA SkillSpector warn 7 Sept 2026
SkillSpector: 5 findings, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

  • medium Excessive Agency · line 75
    Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.
    Fix: Add human-in-the-loop confirmation for destructive, irreversible, or high-impact operations. Never auto-execute commands that modify files, send data, or alter system state.
  • medium Agent Snooping · line 81
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 199
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 198
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
  • medium Agent Snooping · line 200
    Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.
    Fix: Remove all code or instructions that list or read other skills' files or directories. Skills should operate independently; cross-skill access is a privilege escalation.
How audits are shown
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00023 $0.02346
Opus 5 $0.00012 $0.01173
Sonnet 5 $0.00005 $0.00469
Haiku 4.5 $0.00002 $0.00235

Measured 8d ago against content hash 91b1f92e49e5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

payload-experimental-reverts 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 8d 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

plugins/ci/skills/payload-experimental-reverts/SKILL.md · 202 lines

How it starts

The opening of the file, as written. The whole thing — 202 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Payload Experimental Reverts

This skill experimentally tests medium-confidence candidate PRs by opening draft revert PRs, triggering payload jobs, and evaluating results. It operates in two phases separated by a CI wait period. All state is tracked in the payload results YAML file via the payload-results-yaml skill — no separate tracking file is created.

When to Use This Skill

Use this skill when the /ci:payload-experiment command identifies candidate PRs with medium confidence (score 60-84) that cannot be conclusively attributed to a failure through static analysis alone. The experiment creates real tests to determine causality.

Inputs (passed in-context by the caller):

  • results_yaml_path: Path to the payload results YAML file (e.g., ./payload-results-{tag}.yaml)
  • candidates: List of medium-confidence PRs to test experimentally, each with:
    • pr_url, pr_number, component, title, confidence_score
    • failing_jobs: List of {job_name, prow_url, is_aggregated, underlying_job_name}

Required Skills

Before starting, you MUST load the following skills (they define output schemas used when updating results):

  1. payload-results-yaml — schema for the payload results YAML file
  2. payload-autodl-json — schema for the autodl JSON data file

Prerequisites

  1. GitHub CLI (gh): Installed and authenticated
  2. JIRA MCP: Configured for creating TRT issues (needed in Phase 2 for confirmed causes)
  3. Repository Access: User must have push access to their fork of each target repository

Implementation Steps

Phase 1: Set Up Experiments

For each medium-confidence candidate, launch a parallel subagent (do NOT set the model parameter):

1.1: Check for Merge Conflicts

Before opening a revert PR, preemptively check whether the revert will have merge conflicts:

# Clone the repo (shallow for speed)
git clone -b <base_branch> --depth 50 "https://github.com/<org>/<repo>.git" /tmp/experiment-check-<pr_number>
cd /tmp/experiment-check-<pr_number>

# Attempt the revert without committing
git revert -m1 --no-commit <merge_sha>

# Check for conflicts
git status --porcelain

Read the full file on GitHub · 202 lines

Changes

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.

  1. 8d ago First seen · 202 lines · 23 tokens per session scan A 91b1f92e49e5

Subscribe to this mod's changes

payload-experimental-reverts is a skill published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed today), licensed Apache-2.0. It adds 23 tokens to every session and 2,346 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.

Related

Other skills, from other repositories

systematic-debugging

4-phase root cause debugging: understand bugs before fixing.

NousResearch/hermes-agent · 16 tokens

langsmith-observability

LLM observability platform for tracing, evaluation, and monitoring. Use when debugging LLM applications, evaluating model outputs against datasets, monitoring production systems, or building systematic testing pipelines for AI applications.

davila7/claude-code-templates · 45 tokens

experimental-code-coverage-local-debugger

Runs code coverage locally via Universal Test Runner (UTR) or helper scripts, mimicking LUCI trybots. Activate when CQ tryjobs fail or underreport coverage, to test local GN/recipe repairs before uploading, or to debug hermetic crashes.

chromium/chromium · 59 tokens

adversarial-reviewer

Adversarial code review that assumes bugs exist and hunts for them. Use when asked to review code, find bugs, audit for correctness, stress-test a PR, or when someone says "tear this apart" or "what's wrong with this". Give no benefit of the doubt — every line is guilty until proven innocent.

emdash-cms/emdash · 71 tokens

cli-e2e

Write, modify, or debug Docker-based Composio CLI end-to-end tests under ts/e2e-tests/cli, including binary invocation, fixture isolation, output assertions, and package manifests. Use for CLI E2E test suites only; use cli-command for CLI source implementation.

ComposioHQ/composio · 62 tokens

work

Deliver one maintainer-approved EmDash issue, choosing the bug-fix path for a defect and the direct implementation path for an enhancement or task.

emdash-cms/emdash · 31 tokens