payload-experiment

payload-experiment is a command for Claude Code from openshift-eng/ai-helpers. It costs 22 tokens per session (1,019 once invoked), scanned A, original, Apache-2.0.

A command for investigating which code change is causing a failing payload job. It opens temporary draft pull requests that undo medium-confidence changes, then checks the resulting jobs.

In plain words
What is it for?
Use it in a CI payload-triage process after payload analysis. It tests candidates with confidence scores from 60 to 84 and records the experiment status in a YAML results file.
Why use it?
It reduces guesswork when several changes could be responsible for a failure. Confirmed causes become real reverts, while innocent draft reverts are closed.

Command for Claude Code

Written for Claude Code: argument-hint in frontmatter. Also seen: positional $N argument.

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

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.

agentmods
npx agentmods add commands/openshift-eng/ai-helpers/payload-experiment
Clone the repo
git clone --depth 1 https://github.com/openshift-eng/ai-helpers

Made for: Claude Code.

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-experiment

README.md
[![agentmods](https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/payload-experiment.svg)](https://agentmods.dev/commands/openshift-eng/ai-helpers/payload-experiment)
Your own site
<a href="https://agentmods.dev/commands/openshift-eng/ai-helpers/payload-experiment"><img src="https://agentmods.dev/badge/commands/openshift-eng/ai-helpers/payload-experiment.svg" alt="Measured on agentmods" 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 1,019 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
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 $0.00022 $0.01019
Opus 5 $0.00011 $0.00509
Sonnet 5 $0.00004 $0.00204
Haiku 4.5 $0.00002 $0.00102

Measured 6d ago against content hash 70c079dd8377, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, 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 6d 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/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:

  1. /ci:payload-analysis — produces the payload results YAML
  2. /ci:payload-revert — stages reverts for HIGH confidence candidates
  3. /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

  1. Parse the payload tag from the argument. Extract version, stream, and architecture from the tag (see payload-analysis Step 1 for parsing rules).

  2. 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:payload-analysis {payload_tag}` first to generate it.
    
  3. 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.

  1. 6d ago First seen · 82 lines · 22 tokens per session scan A 70c079dd8377

Subscribe to this mod's changes

payload-experiment is a command published in the GitHub repository openshift-eng/ai-helpers (116 stars, last pushed yesterday), licensed Apache-2.0. It adds 22 tokens to every session and 1,019 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 2026-08-30.