Borrowing it
Nothing to install: this file belongs to Triumph-Tech/rock-claude-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.
curl -O https://raw.githubusercontent.com/Triumph-Tech/rock-claude-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/Triumph-Tech/rock-claude-pluginsWrote 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.
[](https://agentmods.dev/instructions/triumph-tech/rock-claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/triumph-tech/rock-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/triumph-tech/rock-claude-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.
<a href="https://agentmods.dev/instructions/triumph-tech/rock-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/triumph-tech/rock-claude-plugins/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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 | $0.01445 | $0.01445 |
| Opus 5.5 | $0.00578 | $0.00578 |
| Sonnet 5.5 | $0.00289 | $0.00289 |
| Haiku 4.5 | $0.00145 | $0.00145 |
Grade A, and why
rock-claude-plugins CLAUDE.md 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 2mo 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.
How it starts
The opening of the file, as written. The whole thing — 97 lines — stays where its author put it; the contents beside it link to each section on GitHub.
rock-claude-plugins: repo guide for Claude
This repo is a Claude Code plugin marketplace for Rock RMS teams and churches. It hosts multiple plugins, each in its own subdirectory, published via the marketplace manifest in .claude-plugin/marketplace.json.
When working in this repo you are almost always authoring or editing skills and commands, not running them. Follow the conventions below.
Your role
You are the author. The contributor is the editor and reviewer. They describe the change they want in plain English; you write the SKILL.md (or command, or manifest edit), update the plugin's README table, handle git, and open PRs with gh when needed. They read the diff and ask for revisions.
By default, do the git and gh work yourself rather than printing commands for the maintainer to run. If they explicitly say they want to drive git themselves, let them. This repo is maintained internally by Triumph Tech; it does not accept outside contributions.
Direct to main vs. pull request
Default to a PR. Take a change direct to main (no branch, no PR) only when it's genuinely small and low-risk:
- Typo fixes, README wording tweaks that don't change meaning, broken links, sentence tightening.
Use a PR for anything that shapes how the team works with Claude:
- Adding, renaming, or removing a skill.
- Changing a skill's trigger description or body guidance in a way that produces different output.
- Plugin manifest edits (
.claude-plugin/). - Cross-cutting changes (new platform directory, restructuring, conventions).
When in doubt, ask the contributor which path they want.
Branch naming
When the change goes via PR, pick the branch name yourself. Format: <initials>/<kebab-short-description>, where <initials> comes from the contributor's name or git config and <kebab-short-description> is 2-5 words summarizing the change (e.g. fix-cdn-example, add-shortcode-skill, rock-ui-update).
One logical change per branch. If the contributor later describes a second unrelated change in the same session, start a fresh branch from main.
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.
- 2mo ago First seen · 97 lines · 1,445 tokens per session scan A e272b1f8a833
rock-claude-plugins CLAUDE.md is an instructions file published in the GitHub repository Triumph-Tech/rock-claude-plugins (2 stars, last pushed 4mo ago), licensed Apache-2.0. It adds 1,445 tokens to every session, about $0.0058 per session on Opus 5.5. 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 2026-08-31.
rock-claude-plugins CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| rock-claude-plugins CLAUDE.mdTriumph-Tech/rock-claude-plugins | Instructions file | 2 | 4mo ago | Apache-2.0 | A | 1,445 | 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 |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | today | MIT | A | 5,516 | GitHub Copilot |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | today | MIT | A | 4,680 | Codex, OpenCode |
| 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 | 3d ago | MIT | A | 4,313 | Codex, OpenCode |