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/posthog/claude-code-share-plugin/claude-mdgit clone --depth 1 https://github.com/PostHog/claude-code-share-pluginWhat 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 | $0.01123 | $0.01123 |
| Opus 5 | $0.00562 | $0.00562 |
| Sonnet 5 | $0.00225 | $0.00225 |
| Haiku 4.5 | $0.00112 | $0.00112 |
Grade B, and why
claude-code-share-plugin CLAUDE.md scanned grade B 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 2d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
cat > ~/.claude/share-plugin-config.json <<EOF How it starts
The opening of the file, as written. The whole thing — 128 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 that converts JSONL session logs into readable markdown and publishes them to GitHub repositories. The plugin provides a /share slash command that executes a Python script to handle the conversion and upload process.
Key Architecture
Plugin Structure
The plugin follows the standard Claude Code plugin architecture:
.claude-plugin/plugin.json: Plugin metadata (name, version, author)commands/share.md: Slash command definition that invokes the Python scriptscripts/share_session.py: Core Python script that handles all functionalityinstall.sh: Automated installer that configures the plugin and saves settings
Core Components
Session Log Discovery (find_latest_session_log() in scripts/share_session.py:31-56):
- Converts current working directory to Claude project directory format (e.g.,
/Users/foo/project→-Users-foo-project) - Searches
~/.claude/projects/{project_dir_name}/*.jsonlfor session files - Falls back to searching all projects if current project directory not found
- Returns most recently modified JSONL file
Configuration System (get_config() in scripts/share_session.py:58-86):
- Priority:
~/.claude/share-plugin-config.json→CLAUDE_SHARE_REPOenv var - Auto-detects GitHub username via
gh api user --jq .login - Returns config dict with: repo, username, branch (defaults to "main"), base_path (defaults to "sessions/claude")
JSONL to Markdown Conversion (convert_jsonl_to_markdown() in scripts/share_session.py:108-213):
- Parses JSONL entries where each line has
{message: {role, content}} - Filters out
/sharecommand artifacts to avoid recursion in shared sessions - Formats user messages as
## Usersections - Formats assistant messages as
## Claudesections - Collapses tool calls in
<details>tags with tool name and JSON input - Skip logic prevents share-related commands/responses from appearing in output
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.
- 2d ago First seen · 128 lines · 1,123 tokens per session scan B 42b492bc5453
claude-code-share-plugin CLAUDE.md is an instructions file published in the GitHub repository PostHog/claude-code-share-plugin (5 stars, last pushed 1mo ago), licensed MIT. It adds 1,123 tokens to every session, about $0.0056 per session on Opus 5. A static security scan graded it B with 1 finding (reads agent configuration directories). 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).
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.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).
next.js AGENTS.md
Instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.