agentmods.dev

deva CLAUDE.md

Repository instructions for Deva, a system that runs coding agents inside isolated Docker containers and uses an issue-based development process.

In plain words
What is it for?
Use them when changing Deva, especially when running Git or GitHub commands and following its container and workflow conventions.
Why use it?
They explain the project's safety boundary and the required steps for issues, commits, pull requests, and releases.

Instructions file

13 5d ago A scan 306 tokens original MIT
View the source file thevibeworks/deva
Install

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.

agentmods
npx agentmods add instructions/thevibeworks/deva/claude-md
Clone the repo
git clone --depth 1 https://github.com/thevibeworks/deva
Per session 306 This file is loaded in full into every session.
When invoked 306 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00306 $0.00306
Opus 5 $0.00153 $0.00153
Sonnet 5 $0.00061 $0.00061
Haiku 4.5 $0.00031 $0.00031

Measured 2d ago against content hash 42f02fa02915, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

deva 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.

CLAUDE.md · 27 lines

What it actually says

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Deva Architecture: Container-Based Agent Sandboxing

CRITICAL DESIGN PATTERN: Deva purposely runs ALL agents inside Docker containers. The container IS the sandbox.

  • Each agent (claude, codex, gemini) runs in isolated container environment
  • Agent internal sandboxes/permission systems are DISABLED (e.g., claude --dangerously-skip-permissions, GEMINI_SANDBOX=false)
  • Container provides security boundary instead of agent-level prompts
  • Result: No interactive permission prompts while maintaining isolation

Why: Avoids permission fatigue in trusted workspaces while keeping agents containerized for safety.

We're following Issue-Based Development (IBD) workflow

  1. Before running any Git/GitHub CLI Bash command (git commit, gh issue create, gh pr create, etc.), open the corresponding file in @workflows to review required steps.
  2. Always apply the exact templates or conventions from the following files:
    • @workflows/GITHUB-ISSUE.md → issues
    • @workflows/GIT-COMMIT.md → commits
    • @workflows/GITHUB-PR.md → pull requests
    • @workflows/RELEASE.md → releases
  3. Keep one branch per issue; merging the PR must auto-close its linked issue.

@./AGENTS.md

Changes

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.

  1. 2d ago First seen · 27 lines · 306 tokens per session scan A 42f02fa02915

Subscribe to this mod's changes

deva CLAUDE.md is an instructions file published in the GitHub repository thevibeworks/deva (13 stars, last pushed 5d ago), licensed MIT. It adds 306 tokens to every session, about $0.0015 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.

DevOps and cloudGit and workflowPlanningclaude-codecodexdeveloper-toolsdockergemini-clishell-script
Related

Other instructions, from other repositories

agent-drop GEMINI.md

Gemini CLI instructions for mikezio/agent-drop: When this repo is configured as an MCP server in a CLI agent.

mikezio/agent-drop · 128 tokens

ai-cli-in-docker AGENTS.md

AGENTS.md instructions for vladborovtsov/ai-cli-in-docker, a project described as: Collection of AI CLI wrappers: Run AI CLI tools (OpenAI Codex, Google Gemini, OpenCode, Claude Code) inside Docker to keep your host clean while persisting CLI auth/config on your machine.

vladborovtsov/ai-cli-in-docker · 4 tokens

prompt-tracker GEMINI.md

Gemini CLI instructions for DaRabus/prompt-tracker, covering gemini.md, project overview, architecture, build & test commands and full stack.

DaRabus/prompt-tracker · 1,914 tokens

prompt-tracker AGENTS.md

AGENTS.md instructions for DaRabus/prompt-tracker, covering agents.md, project, mandatory rules, rule 1 — always update tests and rule 2 — always update readme.md.

DaRabus/prompt-tracker · 2,071 tokens

prompt-tracker copilot-instructions.md

Copilot instructions for DaRabus/prompt-tracker, covering github copilot instructions, project, agent skills index, project skills and external skills.

DaRabus/prompt-tracker · 962 tokens

prompt-tracker CLAUDE.md

Claude Code instructions for DaRabus/prompt-tracker, covering claude.md, quick reference, claude-specific behavior, tool usage and skills are mandatory.

DaRabus/prompt-tracker · 827 tokens