What is agent-plugins CLAUDE.md?

Repository instructions for developing skills in the konflux-ci/agent-plugins project. They describe the repository, its structure, development guidance, and test-driven development, or TDD, for documentation.

Use them when developing or reviewing skills in that project, especially when writing documentation tests before or alongside the documentation.

They give contributors shared rules for changing the repository and checking documentation changes.

How konflux-ci/agent-plugins configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to konflux-ci/agent-plugins. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/konflux-ci/agent-plugins/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/konflux-ci/agent-plugins

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/instructions/konflux-ci/agent-plugins/claude-md/github.svg)](https://agentmods.dev/instructions/konflux-ci/agent-plugins/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/konflux-ci/agent-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/konflux-ci/agent-plugins/claude-md/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/instructions/konflux-ci/agent-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/konflux-ci/agent-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 3,560 This file is loaded in full into every session.

When invoked 3,560 The same file — it is already loaded in full.

Security scan C 1 finding. A grade says what 26 rules found in the file — not that it is safe.

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.

Model	Per session	Once invoked
Fable 5.1	$0.03560	$0.03560
Opus 5.5	$0.01424	$0.01424
Sonnet 5.5	$0.00712	$0.00712
Haiku 4.5	$0.00356	$0.00356

Measured 1mo ago against content hash 96f2ba417fdc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

agent-plugins CLAUDE.md scanned grade C with 1 finding 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 1mo 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.

Reaches for credential fileshighPrivilege escalation

SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.

- `.aws/credentials` - AWS CLI credentials

CLAUDE.md · 387 lines

How it starts

The opening of the file, as written. The whole thing — 387 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Konflux Skills Repository

Purpose

This repository contains Claude Code skills to help users work with the Konflux CI/CD platform. Skills provide quick reference materials, techniques, and patterns for common Konflux workflows.

Target audience: Developers and platform engineers using Konflux for continuous integration, testing, and release management.

Testing Approach: Realistic Skill Discovery with Parallel Execution

Solution: Tests verify that Claude will discover and invoke skills in realistic scenarios using isolated temp HOME directories per worker.

How it works:

Create N temp HOME directories (one per parallel worker)
Each worker HOME contains:
- Symlink to skill in ~/.claude/skills/
- Copy of .config/gcloud (required for Claude Code API auth)
- Skill-specific credentials from copy_to_home field (e.g., .config/gh)
Run claude --print --allowed-tools=<tools> with HOME=/tmp/claude-worker-N/
- Parses allowed-tools from SKILL.md frontmatter
- Always includes Skill tool plus any skill-specific tools
Each worker reuses its temp HOME across all test invocations
Cleanup all worker HOMEs after test completion

Key insights:

Isolated temp HOMEs prevent file watcher conflicts between parallel workers
Skills symlinked to ~/.claude/skills/ are discovered automatically
Tool permissions: Test framework parses allowed-tools from SKILL.md frontmatter
Credentials: Test framework copies paths from scenarios.yaml copy_to_home field
.config/gcloud always copied for Claude Code API authentication
Skill-specific credentials (gh, kubectl, etc.) declared per skill
Worker HOMEs persist for the duration of the test run

Benefits:

✅ Tests real skill discovery (Claude loads skills from ~/.claude/skills/)
✅ Works in --print mode (automated testing)
✅ True parallel execution (8 workers, isolated file watchers)
✅ Runs from /tmp to avoid loading CLAUDE.md from repository
✅ Each worker reuses setup (minimal overhead per test)

Read the full file on GitHub · 387 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.

1mo ago Changed · -9 tokens per session 96f2ba417fdc
2mo ago First seen · 387 lines · 3,569 tokens per session scan C b1da29c61de4

Subscribe to this mod's changes

agent-plugins CLAUDE.md is an instructions file published in the GitHub repository konflux-ci/agent-plugins (9 stars, last pushed 4d ago), licensed Apache-2.0. It adds 3,560 tokens to every session, about $0.0142 per session on Opus 5.5. A static security scan graded it C with 1 finding (reaches for credential files). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Building agents

agent-plugins CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
agent-plugins CLAUDE.mdkonflux-ci/agent-plugins	Instructions file	9	4d ago	Apache-2.0	C	3,560	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

agent-plugins: Instructions file for Claude Code