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/skycube/junebug/claude-mdgit clone --depth 1 https://github.com/skycube/junebugWhat 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 | $0.00754 | $0.00754 |
| Opus 5 | $0.00377 | $0.00377 |
| Sonnet 5 | $0.00151 | $0.00151 |
| Haiku 4.5 | $0.00075 | $0.00075 |
Grade A, and why
junebug 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 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.
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 — 49 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.
What this repo is
Junebug is a Claude Code skill — a plain-text prompt file that makes an AI agent reply in plain, concise language for readers with a limited attention span and/or smaller vocabulary. There is no code to build, no package manager, and no test suite. All meaningful content lives in these files:
skills/junebug/SKILL.md— the agent-facing instructions (the actual skill); single source of truth for behaviorskills/junebug/README.md— human-facing docs shown in the skill marketplaceREADME.md— the public project README with install instructions, before/after examples, and benchmarksAGENTS.md— auto-injectsSKILL.mdinto agents that support the@includeconvention (Codex, Amp, Jules, etc.)GEMINI.md— same asAGENTS.mdbut for Gemini CLIplugin.json— plugin manifest for the generic agent plugin marketplace.claude-plugin/plugin.json— Claude Code plugin manifest (name, description, author; no hooks).claude-plugin/marketplace.json— Claude Code marketplace listing (category, short description shown in search results)
bak.junebug/ is a backup copy of the repo root; ignore it.
How the skill works
SKILL.md is loaded into an agent's context when the user invokes /junebug or says "junebug mode." It instructs the agent to:
- Run every reply through a compression filter (cut filler, hedging, politeness, tool-call narration)
- Enforce a word budget:
fullmode ~150 words,litemode ~300 words - Cap answer options at 3 with a "Read more?" escape hatch
- Auto-pause compression for security-relevant content, anything requiring explicit approval, or where compression risks a misread (destructive commands, ordering-sensitive steps) — resume right after
- Never apply compression to code, commits, PRs, or external-facing docs
The description: frontmatter block in SKILL.md controls when Claude Code auto-triggers the skill.
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 · 49 lines · 754 tokens per session scan A fc6050df23bd
junebug CLAUDE.md is an instructions file published in the GitHub repository skycube/junebug (5 stars, last pushed 21d ago), licensed MIT. It adds 754 tokens to every session, about $0.0038 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
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.
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
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, applying the notice (cutover) and fallback chain (never fail the build).
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.
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.