Payload Experimental Reverts

Payload Experimental Reverts is a skill for Claude Code, Codex from wangke19/gemini-ai-helpers. It costs 22 tokens per session (2,345 once invoked), scanned A, a copy of payload-experimental-reverts, Apache-2.0.

A method for testing uncertain causes of payload failures by creating draft pull requests that revert suspected changes and then running payload jobs. A payload is a tested set of software changes.

In plain words
What is it for?
Testing medium-confidence candidate pull requests, triggering the related payload jobs, comparing the results, and recording the outcome in the payload results YAML file.
Why use it?
It uses a controlled CI experiment when log analysis alone cannot show whether a change caused the failure.

Skill for Claude CodeCodex

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

Good fit Testing medium-confidence candidate pull requests, triggering the related payload jobs, comparing the results, and recording the outcome in the payload results YAML file.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/wangke19/gemini-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 wangke19/gemini-ai-helpers --skill payload-experimental-reverts
Clone the repo
git clone --depth 1 https://github.com/wangke19/gemini-ai-helpers

Made for: Claude Code, Codex.

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/wangke19/gemini-ai-helpers/payload-experimental-reverts/github.svg)](https://agentmods.dev/skills/wangke19/gemini-ai-helpers/payload-experimental-reverts)
Your own site
<a href="https://agentmods.dev/skills/wangke19/gemini-ai-helpers/payload-experimental-reverts"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-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/wangke19/gemini-ai-helpers/payload-experimental-reverts"><img src="https://agentmods.dev/badge/skills/wangke19/gemini-ai-helpers/payload-experimental-reverts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 22 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,345 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.
Origin 97% copy Near-identical to another mod 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 $0.00022 $0.02345
Opus 5 $0.00011 $0.01172
Sonnet 5 $0.00004 $0.00469
Haiku 4.5 $0.00002 $0.00234

Measured 11d ago against content hash 7b09cdbb8835, 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 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.

Origin

This is a copy

97% identical to payload-experimental-reverts — 12 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.

extensions/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. 11d ago First seen · 202 lines · 22 tokens per session scan A 7b09cdbb8835

Subscribe to this mod's changes

Payload Experimental Reverts is a skill published in the GitHub repository wangke19/gemini-ai-helpers (2 stars, last pushed 5mo ago), licensed Apache-2.0. It adds 22 tokens to every session and 2,345 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to payload-experimental-reverts, differing in 12 lines, and is treated as a copy.