Borrowing it
Nothing to install: this file belongs to technicalpickles/pickled-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/technicalpickles/pickled-claude-plugins/main/CLAUDE.mdgit clone --depth 1 https://github.com/technicalpickles/pickled-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/technicalpickles/pickled-claude-plugins/claude-md)<a href="https://agentmods.dev/instructions/technicalpickles/pickled-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/technicalpickles/pickled-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/technicalpickles/pickled-claude-plugins/claude-md"><img src="https://agentmods.dev/badge/instructions/technicalpickles/pickled-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 | $0.02419 | $0.02419 |
| Opus 5.5 | $0.00968 | $0.00968 |
| Sonnet 5.5 | $0.00484 | $0.00484 |
| Haiku 4.5 | $0.00242 | $0.00242 |
Grade D, and why
pickled-claude-plugins CLAUDE.md scanned grade D with 2 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`CLAUDE_PLUGIN_ROOT` (the plugin's cache directory) is set for plugin hooks only, NOT for global hooks in `~/.claude/settings.json`. Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
If `installed_plugins.json` points at a path that doesn't exist (seen with directory-source marketplaces), `rm -rf ~/.claude/plugins/cache/pickled-claude-plugins/{plugin}/` and reinstall. How it starts
The opening of the file, as written. The whole thing — 141 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Claude Code Plugins Monorepo
This repository contains Claude Code plugins for the pickled-claude-plugins.
Repository Structure
plugins/
└── {name}/ # One directory per local plugin. Canonical list: README.md "## Plugins" (generated).
Development vs Installation
Installed plugins are copied to ~/.claude/plugins/cache/{marketplace}/{plugin}/{version}/, so changes to local source take effect only after a reinstall and a Claude Code restart:
/plugin uninstall {plugin}@pickled-claude-plugins
/plugin install {plugin}@pickled-claude-plugins
To run a hook against local source, set CLAUDE_PLUGIN_ROOT="$PWD/plugins/{name}" (Claude Code sets it automatically for installed plugins).
If installed_plugins.json points at a path that doesn't exist (seen with directory-source marketplaces), rm -rf ~/.claude/plugins/cache/pickled-claude-plugins/{plugin}/ and reinstall.
Changing a routes.json or tool-routes.yaml? Test it with the tool-routing CLI: plugins/tool-routing/docs/route-discovery.md covers tool-routing test/list, CLAUDE_PROJECT_ROOT, and why local-scoped plugins need an exact projectPath match.
Shell scripts must run on bash 3.2
macOS ships /bin/bash 3.2, and #!/usr/bin/env bash can resolve to it even with a newer Homebrew bash installed. So no declare -A, mapfile, ${var,,}, |&, etc. — use parallel indexed arrays or a delimited string instead of associative arrays. ./scripts/check-bash-compat.sh flags these (CI and the hk pre-commit hook run it); test locally with /bin/bash path/to/script. It can't catch "${arr[@]}" on an empty array under set -u, which also errors on bash < 4.4.
Environment Variables
CLAUDE_PLUGIN_ROOT (the plugin's cache directory) is set for plugin hooks only, NOT for global hooks in ~/.claude/settings.json.
Hooks/plugins reading user-level config must honor CLAUDE_CONFIG_DIR. It's undocumented (not in Claude Code's env-vars/settings docs as of 2026-07) but honored in practice, and it replaces ~/.claude rather than adding to it; it accepts a single dir or a :/,-separated list to search in order. Resolve as $CLAUDE_CONFIG_DIR (split on [:,]) or [$HOME/.claude]; don't hardcode $HOME/.claude, or config lookup silently breaks the day a user relocates their config dir. See plugins/writing-tools/src/writing_tools/config.py's _user_config_dirs() for a working implementation (PR #102).
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.
- yesterday Changed · -93 lines · -758 tokens per session 3a13a47107db
- 1mo ago Changed · +4 lines · +145 tokens per session fdf5b8ed4ab6
- 1mo ago Changed · +18 lines · +306 tokens per session 9e7e7f82f396
- 1mo ago Changed · +20 lines · +804 tokens per session 9c9347033103
- 2mo ago First seen · 192 lines · 1,922 tokens per session scan D 880fac77b54f
pickled-claude-plugins CLAUDE.md is an instructions file published in the GitHub repository technicalpickles/pickled-claude-plugins (12 stars, last pushed yesterday), licensed MIT. It adds 2,419 tokens to every session, about $0.0097 per session on Opus 5.5. A static security scan graded it D with 2 findings (reads agent configuration directories, recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
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).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.