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/fletchgqc/agentbox/claude-mdgit clone --depth 1 https://github.com/fletchgqc/agentboxWrote 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/fletchgqc/agentbox/claude-md)<a href="https://agentmods.dev/instructions/fletchgqc/agentbox/claude-md"><img src="https://agentmods.dev/badge/instructions/fletchgqc/agentbox/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 | $0.00425 | $0.00425 |
| Opus 5 | $0.00212 | $0.00212 |
| Sonnet 5 | $0.00085 | $0.00085 |
| Haiku 4.5 | $0.00042 | $0.00042 |
Grade A, and why
agentbox 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 — 34 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Read @DEVELOPMENT_NOTES.md to understand the project.
Collaboration Style
- Exercise full agency to push back on mistakes. Flag issues early, ask questions if unsure of direction instead of choosing randomly.
- Eliminate emojis, praise, filler, hype.
- Don't flatter me. Give me honest feedback even if I don't want to hear it.
Code comments
Code comments are used sparingly in this project, since they add to code bloat. Comprehensible and expressive code (eg. consistent, logical naming) is preferred to comments.
Comments are still added when they contribute to much faster, better understanding in two cases:
- To explain why something was done, when it is not apparent from the context.
- To explain what is being done, if the code is necessarily difficult to understand for an advanced programmer or agent.
If a log line is written explaining what is happening, any comment above that line which essentially says the same thing is removed, since a developer has the same information from the log line.
Developers challenge comments to ensure they match the criteria. Existing comments are cleaned up according to the boy-scout rule.
Documentation
The user documentation (README.md) is concise, delivering maximum meaning with a minimum amount of words and examples.
The documentation follows these principles:
- assume the reader is a knowledgeable developer.
- good: document each available command line flag, assume reader will combine as needed.
- bad: give examples of many combinations command-line flags.
- document agentbox-specific knowledge, do not replicate standard claude code documentation.
- good: "mcp servers are supported according to standard syntax"
- bad: "here is the syntax of a claude code mcp server file"
- aim to inform the user of genuinely important/helpful information, not promote the project by listing every internal implementation detail.
- weigh additions against the knowledge that the longer the documentation is, the less likely that anyone will read it at all.
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 · 34 lines · 425 tokens per session scan A 03cb6c306ce9
agentbox CLAUDE.md is an instructions file published in the GitHub repository fletchgqc/agentbox (113 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 425 tokens to every session, about $0.0021 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 2026-08-30.
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.