What is payload-experiment?

A two-stage experiment for finding which pull request caused a failing payload, meaning a tested build assembled from multiple changes. It opens draft revert pull requests for candidates and uses later CI results to confirm or dismiss them.

Use it after payload analysis to test medium-confidence candidates, promote confirmed causes to real reverts, and close draft reverts for changes that were not responsible.

When several changes may be responsible, testing them one by one can identify the cause without immediately reverting every candidate. The command records experiment status in the payload results YAML file.

payload-experiment — Command for Claude Code by wangke19

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.

Clone the repo

git clone --depth 1 https://github.com/wangke19/gemini-ai-helpers

Made for: Claude Code.

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.

README.md

[![agentmods](https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/payload-experiment/github.svg)](https://agentmods.dev/commands/wangke19/gemini-ai-helpers/payload-experiment)

Your own site

<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/payload-experiment"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/payload-experiment/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.

Your own site · 80×15

<a href="https://agentmods.dev/commands/wangke19/gemini-ai-helpers/payload-experiment"><img src="https://agentmods.dev/badge/commands/wangke19/gemini-ai-helpers/payload-experiment.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 22 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.

When invoked 996 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 94% 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.

Model	Per session	Once invoked
Fable 5.1	$0.00022	$0.00996
Opus 5	$0.00011	$0.00498
Sonnet 5	$0.00004	$0.00199
Haiku 4.5	$0.00002	$0.00100

Measured 8d ago against content hash 19cbfa65bc01, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

payload-experiment 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

This is a copy

94% identical to payload-experiment — 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/commands/payload-experiment.md · 82 lines

How it starts

The opening of the file, as written. The whole thing — 82 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Name

ci:payload-experiment

Synopsis

/ci:payload-experiment <payload-tag>

Description

The ci:payload-experiment command opens draft revert PRs for medium-confidence payload candidates (confidence score 60-84) and triggers payload jobs to experimentally determine which PR is causing failures. It operates in two phases separated by a CI wait period.

Phase 1: Reads the payload results YAML, filters medium-confidence candidates, opens draft revert PRs, triggers payload jobs, and appends action entries (type: "experiment", status: "pending") to each candidate's actions array.

Phase 2: Detects candidates with a status: "pending" action entry in the results YAML, checks job results, promotes confirmed causes to real revert PRs (with TRT JIRA bugs), and closes innocent draft PRs.

All state is tracked in the payload results YAML via the payload-results-yaml skill — no separate tracking file is created.

This command is one of three composable stages in the payload triage pipeline:

/ci:analyze-payload — produces the payload results YAML
/ci:payload-revert — stages reverts for HIGH confidence candidates
/ci:payload-experiment — experimentally tests MEDIUM confidence candidates (this command)

Job Triggering Limits

Non-aggregated jobs: Up to 5 total across all candidates
Aggregated jobs: Up to 1 total

Implementation

Parse the payload tag from the argument. Extract version, stream, and architecture from the tag (see analyze-payload Step 1 for parsing rules).
Read the payload results YAML using the payload-results-yaml skill: Look for payload-results-{tag}.yaml in the current working directory. If not found, print an error and exit:
```
Error: Payload results YAML not found for {payload_tag}.
Run `/ci:analyze-payload {payload_tag}` first to generate it.
```
Detect Phase 2 resume: If the results YAML contains any action entry with type: "experiment" and status: "pending", jump to Phase 2 (step 5). Phase 2 processes only pending experiments — candidates with other statuses are left unchanged.

Read the full file on GitHub · 82 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.

8d ago First seen · 82 lines · 22 tokens per session scan A 19cbfa65bc01

Subscribe to this mod's changes

payload-experiment is a command 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 996 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. It is 94% identical to payload-experiment, differing in 12 lines, and is treated as a copy.

Debugging extentions gemini-cli openshift redhat

audit

Run a structured codebase audit. Maps the architecture, assesses health (compliance, tests, docs), performs deep analysis (security, performance, code quality), and synthesizes a prioritized roadmap. Outputs land under docs/audit/ in this project. Phases 0-3 with human checkpoints between each phase. Use /audit-quick…

telus-labs/stagecraft · 78 tokens

payload-experiment