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.
npx agentmods add instructions/jeffrigby/somepulp-agents/claude-mdgit clone --depth 1 https://github.com/jeffrigby/somepulp-agentsWrote 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/jeffrigby/somepulp-agents/claude-md)<a href="https://agentmods.dev/instructions/jeffrigby/somepulp-agents/claude-md"><img src="https://agentmods.dev/badge/instructions/jeffrigby/somepulp-agents/claude-md.svg" alt="Measured on agentmods" 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 | $0.01672 | $0.01672 |
| Opus 5 | $0.00836 | $0.00836 |
| Sonnet 5 | $0.00334 | $0.00334 |
| Haiku 4.5 | $0.00167 | $0.00167 |
Grade A, and why
somepulp-agents 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 4d 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 — 165 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Claude Code plugin marketplace called somepulp-agents that provides specialized AI agents and skills for code auditing, documentation maintenance, and library/API research.
Repository Structure
This is a plugin marketplace containing multiple independent plugins:
somepulp-agents/
├── .claude-plugin/marketplace.json # Marketplace manifest
├── plugins/
│ ├── codebase-health/ # Code auditing & documentation
│ └── research-assistant/ # Library/API research with MCP
├── CLAUDE.md # This file
├── README.md # User-facing documentation
└── CHANGELOG.md # Version history
Each plugin follows the standard structure:
.claude-plugin/plugin.json- Plugin manifest (metadata only; agents/commands/skills are auto-discovered from their default directories, not enumerated in the manifest)agents/- Markdown agents with YAML frontmattercommands/- Slash command definitionsskills/- Skills with reference documentationscripts/- Helper shell scripts (optional)
Agent and Skill Format
Agent Files (agents/*.md)
---
name: agent-name
description: One-line trigger description. Use when user asks "X", "Y", or "Z".
tools: ["Read", "Grep", "Glob", "Bash"]
model: inherit
color: blue
---
System prompt content defining agent behavior...
## Example Invocations
<example>
Context: ...
user: "..."
assistant: "..."
</example>
Important: Keep description to a single line. Multi-line content (especially <example> blocks) belongs in the body, not the frontmatter — descriptions are truncated at 1,536 characters for auto-routing decisions, so embedded examples get cut off.
Skill Files (skills/*/SKILL.md)
---
name: skill-name
description: What the skill does and which use cases it covers (use-case-first)
when_to_use: Trigger phrases, e.g. when the user asks to "X", "Y", or "Z"
allowed-tools: Read, Grep, Glob, Bash
---
Skill methodology and guidance...
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.
- 4d ago First seen · 165 lines · 1,672 tokens per session scan A 3979dc9a15ff
somepulp-agents CLAUDE.md is an instructions file published in the GitHub repository jeffrigby/somepulp-agents (7 stars, last pushed 2mo ago), licensed MIT. It adds 1,672 tokens to every session, about $0.0084 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 2026-08-31.
Other instructions, from other repositories
craftsman-marketplace CLAUDE.md
Claude Code instructions for gul-labs/craftsman-marketplace, covering claude.md, editing rules and design principles (non-negotiable).
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.