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/alexandermattturner/agent-glovebox/claude-mdgit clone --depth 1 https://github.com/AlexanderMattTurner/agent-gloveboxWhat 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 | $0.15868 | $0.15868 |
| Opus 5 | $0.07934 | $0.07934 |
| Sonnet 5 | $0.03174 | $0.03174 |
| Haiku 4.5 | $0.01587 | $0.01587 |
Grade C, and why
agent-glovebox CLAUDE.md scanned grade C 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 today.
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.
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`. Prefer the Write tool for files. The Bash sandbox blocks `.claude/hooks`, credential directories, and `~/.config/gh`; batch commit, pus How it starts
The opening of the file, as written. The whole thing — 188 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 sbx 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 |
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.
- today Changed · +61 tokens per session 13e9f7d7b4ce
- yesterday First seen · 188 lines · 15,807 tokens per session scan C 613a8f0ed11d
agent-glovebox CLAUDE.md is an instructions file published in the GitHub repository AlexanderMattTurner/agent-glovebox (57 stars, last pushed today), licensed Apache-2.0. It adds 15,868 tokens to every session, about $0.0793 per session on Opus 5. A static security scan graded it C with 1 finding (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
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.
buildNext
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
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
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.