harness:cicd-fleet

harness:cicd-fleet is a command for Claude Code from Intense-Visions/harness-engineering. It costs 91 tokens per session (645 once invoked), scanned A, original, MIT.

An automated coordinator for investigating failed continuous integration and delivery checks and flaky tests. CI/CD checks code automatically, while a flaky test passes or fails unpredictably.

In plain words
What is it for?
Use it to triage red CI/CD runs, investigate flaky tests, run deflake or workflow repairs, and return verified remediation branches for review.
Why use it?
It organizes failures by cause, assigns isolated repair work, and verifies that fixes pass the required checks across operating systems.

Command for Claude Code

Written for Claude Code: allowed-tools in frontmatter. Also seen: mentions subagents.

Part of the harness-claude plugin — 85 skills, 89 commands, 17 agents, 4 hooks, 4 MCP servers 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/intense-visions/harness-engineering/cicd-fleet
Clone the repo
git clone --depth 1 https://github.com/Intense-Visions/harness-engineering

Made for: Claude Code.

Or install harness-claude, the plugin that ships this one along with the rest of its 85 skills, 89 commands, 17 agents, 4 hooks, 4 MCP servers.

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 harness:cicd-fleet

README.md
[![agentmods](https://agentmods.dev/badge/commands/intense-visions/harness-engineering/cicd-fleet.svg)](https://agentmods.dev/commands/intense-visions/harness-engineering/cicd-fleet)
Your own site
<a href="https://agentmods.dev/commands/intense-visions/harness-engineering/cicd-fleet"><img src="https://agentmods.dev/badge/commands/intense-visions/harness-engineering/cicd-fleet.svg" alt="Measured on agentmods" height="20"></a>
Per session 91 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 645 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 $0.00091 $0.00645
Opus 5 $0.00046 $0.00322
Sonnet 5 $0.00018 $0.00129
Haiku 4.5 $0.00009 $0.00064

Measured 6d ago against content hash 1b9cd2b1f8d2, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

harness:cicd-fleet 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.

.claude-plugin/commands/cicd-fleet.md · 41 lines

What it actually says

Phases:

  • select: Enumerate red CI/CD runs and flaky-test signals via gh, classify each into the red-cause taxonomy (real-failure / flake / infra-config / already-green / needs-design), cross-check for already-green/superseded runs, and order remediable candidates by impact via roadmap-pilot scoring
  • confirm: Present the triaged queue in one round — remediable items with their cause buckets, already-green items flagged for closure, needs-design items flagged to park, decision forks as questions, proposed concurrency — for a single up-front human approval
  • dispatch: Fan out worktree-isolated subagents, each running the real harness-debugging (heal/deflake) or harness-workflow-audit (infra/config) pipeline for one item, capped at the concurrency governor; an un-deflakable flake or unforeseen fork parks and reports rather than hiding the failure
  • verify: Independently confirm each returned branch has a plan artifact plus autopilot-state and is CI-green across all target operating systems plus the project's required checks — with deterministic repeated-run green for deflakes — never by subagent self-report
  • report: Emit a one-row-per-item batch summary with remediation-actions notes for bulk human review, close already-green/superseded runs citing the resolving run/PR, and never merge

<execution_context> @agents/skills/claude-code/cicd-fleet/SKILL.md @agents/skills/claude-code/cicd-fleet/skill.yaml </execution_context>

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 · 41 lines · 91 tokens per session scan A 1b9cd2b1f8d2

Subscribe to this mod's changes

harness:cicd-fleet is a command published in the GitHub repository Intense-Visions/harness-engineering (20 stars, last pushed yesterday), licensed MIT. It adds 91 tokens to every session and 645 once invoked, about $0.0005 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.