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/eduardoarantes/agentenv/claude-mdgit clone --depth 1 https://github.com/eduardoarantes/agentenvWhat 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 | $0.02213 | $0.02213 |
| Opus 5 | $0.01107 | $0.01107 |
| Sonnet 5 | $0.00443 | $0.00443 |
| Haiku 4.5 | $0.00221 | $0.00221 |
Grade A, and why
agentenv Development Guide 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 — 252 lines — stays where its author put it; the contents beside it link to each section on GitHub.
agentenv Development Guide
This file describes the three development areas of agentenv — the Rust CLI (agentenv), the core library (agentenv-core), and the VS Code extension (vscode) — and the conventions, scope, and useful commands for each.
Development areas
Rust core and CLI
Purpose: Rust core library and CLI development with TDD focus
Scope:
crates/agentenv-core/- Core library logiccrates/agentenv-cli/- CLI implementation- Unit tests and integration tests
Skills:
- Test-driven development (write tests first)
- Error handling with
thiserror - Async/await with tokio
- Configuration parsing (YAML/JSON)
- File system operations
Commands:
cargo test- Run all testscargo clippy- Lint checkscargo fmt- Format codecargo build- Build project
VS Code extension
Purpose: VS Code extension development
Scope:
vscode/src/- TypeScript extension code- Extension manifest and configuration
- Integration with agentenv CLI
Skills:
- VS Code API knowledge
- TypeScript strict mode
- ESLint and Prettier formatting
- Extension lifecycle (activation, deactivation)
- Command registration
Commands:
npm run compile- Compile TypeScriptnpm run lint- ESLint checksnpm run format- Prettier formatting
CLI ↔ extension integration
Purpose: Design and implement integration between CLI and extension
Scope:
- Cross-crate communication
- Plugin resolution flow
- Symlink management
- Target-tool integration
Skills:
- Architectural patterns
- API design
- Error propagation
- Configuration synchronization
Commands:
- Document integration points
- Design data flows
- Implement error contracts
Source-driven canonical pipelines
.agentrc.yaml declares a single source: <tool> — currently claude-code.
For every capability (hooks, skills, agents), sync:
- Reads the source's native layout losslessly into a canonical YAML under
<project>/.agentenv/<capability>.canonical.yaml. Open-map frontmatter plus an explicitNative-style escape hatch (for hooks) ensure no information is dropped between source and canonical. - Renders the canonical out to every configured non-source target via
per-capability writers. Each writer reports
dropsfor fields/items it cannot represent; nothing is silently lost.
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 · 252 lines · 2,213 tokens per session scan A 72436f0af1e1
agentenv Development Guide is an instructions file published in the GitHub repository eduardoarantes/agentenv (5 stars, last pushed 3mo ago), licensed MIT. It adds 2,213 tokens to every session, about $0.0111 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
claude-code-plugins AGENTS.md
AGENTS.md instructions for melodic-software/claude-code-plugins, covering claude-code-plugins, validate a change and conventions that load on demand.
claude-code-plugins CLAUDE.md
Claude Code instructions for melodic-software/claude-code-plugins, a project described as: Melodic Software — Claude Code plugin marketplace: reusable, repo-agnostic skills, hooks, agents, and MCP servers.
amfs CLAUDE.md
Instructions for raia-live/amfs, covering amfs memory — agent instructions, available mcp tools, identity, brain tools (agent-scoped) and shared knowledge tools.
agentor copilot-instructions.md
Instructions for CelestoAI/agentor: Read AGENTS.md in the repository root. It is the single source of contributor guidance for this project — architecture, development setup, code style, testing, and CI — and applies to Copilot exactly as written.
atlas AGENTS.md
Instructions for atlas-php/atlas, covering agents, before you work, hard gates — require explicit approval, never and tech stack.
best-of-Agent-Harnesses CLAUDE.md
Claude Code instructions for RyanAlberts/best-of-Agent-Harnesses, covering repo notes for ai coding agents, commit identity (required), branching and pushing (required), verifying contribution credit (required) and how the list is generated.