Borrowing it
Nothing to install: this file belongs to AlexanderMattTurner/agent-glovebox. 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/AlexanderMattTurner/agent-glovebox/main/CLAUDE.mdgit clone --depth 1 https://github.com/AlexanderMattTurner/agent-gloveboxWrote 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/alexandermattturner/agent-glovebox/claude-md)<a href="https://agentmods.dev/instructions/alexandermattturner/agent-glovebox/claude-md"><img src="https://agentmods.dev/badge/instructions/alexandermattturner/agent-glovebox/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/alexandermattturner/agent-glovebox/claude-md"><img src="https://agentmods.dev/badge/instructions/alexandermattturner/agent-glovebox/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 | $0.16835 | $0.16835 |
| Opus 5.5 | $0.06734 | $0.06734 |
| Sonnet 5.5 | $0.03367 | $0.03367 |
| Haiku 4.5 | $0.01683 | $0.01683 |
Grade D, and why
agent-glovebox CLAUDE.md scanned grade D with 3 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.
- **Fix the cause, not the instance.** A re-run, a re-dispatch, a retry, a widened matcher or a longer timeout each leaves the cause reachable. Name the mechanism that produced the wrong answer, then change that mechanis Enumerates other installed skillsmediumAgent snooping
Other skills' SKILL.md files reveal prompts, capabilities and secrets that should be invisible to peers.
**A RED CHECK'S LOG ALREADY NAMES WHAT FAILED — READ IT, and run NOTHING locally to find out.** The [`ci-triage` skill](.claude/skills/ci-triage/SKILL.md) owns the routes to it. Run the targeted test only AFTER the log n Recursive force deletehighDestructive command
rm -rf with a variable or a broad path is one typo away from removing the wrong tree.
On the host, never run `rm -rf`. Use a unique scratch directory under `/tmp/claude`. **A WORKTREE goes under `/tmp/claude-worktrees` instead, created with `umask 002`.** `/tmp/claude` is closed to other users (0700 on th How it starts
The opening of the file, as written. The whole thing — 285 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
glovebox wraps a coding agent in a sandbox you can leave running unattended: a signed-image microVM (the Kata backend) with an outgoing-traffic firewall, a second model watching the tool stream, and guardrail hooks that gate each tool call. Every layer that judges a tool call fails closed; the skill-gate reminders, which only say what to read first, do not. Most of this repo is that machinery plus the CI that proves it still engages.
Where the rest of the guidance lives
This file carries only what applies to every session.
| Surface | Loads when | Owns |
|---|---|---|
.github/CLAUDE.md |
you open a file under .github/ |
workflow authoring: job naming, externalized run: scripts, paths:/reporter/concurrency mechanics, required-check sync, no-conditional-checks |
.claude/rules/ |
you open a file its paths: glob matches |
code-style.md (any source file), shell-style.md, python-style.md, changelog.md, sandbox-runtime.md, hooks-control-plane.md, prompt-authoring.md (this file, a rule, a skill, an agent prompt), and the rest |
.claude/skills/ |
you invoke it (some are forced by a gate-*-skill PreToolUse hook) |
the mechanics of an activity: pr-creation, git-workflow, babysit-prs, ci-triage, writing-tests, defect-to-guard, explore-plan, doctrine-capture (a capitalised NEVER or ALWAYS, or a complaint about how the session ran) |
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 · +46 tokens per session 018d7e97326d
- 3d ago Changed · -10 tokens per session e93fcacdfb78
- 5d ago Changed · +40 tokens per session 278fb2ea54fc
- 6d ago Changed · +101 tokens per session bd1eb142fc0c
- 8d ago Changed · +3 lines · +290 tokens per session 7ca01add1bf9
- 9d ago Changed · +46 tokens per session 942685462e11
- 10d ago Changed · +1 lines · +158 tokens per session 61eed857b558
- 11d ago Changed · -2 tokens per session 23d000dc0c59
- 12d ago Changed · +38 tokens per session acb807a55f9f
- 13d ago First seen · 281 lines · 16,128 tokens per session scan D 3fda6f038034
agent-glovebox CLAUDE.md is an instructions file published in the GitHub repository AlexanderMattTurner/agent-glovebox (68 stars, last pushed today), licensed Apache-2.0. It adds 16,835 tokens to every session, about $0.0673 per session on Opus 5.5. A static security scan graded it D with 3 findings (reads agent configuration directories, enumerates other installed skills, recursive force delete). 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).
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).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.