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/rossumai/rossum-agents/agents-mdgit clone --depth 1 https://github.com/rossumai/rossum-agentsWrote 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/rossumai/rossum-agents/agents-md)<a href="https://agentmods.dev/instructions/rossumai/rossum-agents/agents-md"><img src="https://agentmods.dev/badge/instructions/rossumai/rossum-agents/agents-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 5.1 | $0.03215 | $0.03215 |
| Opus 5 | $0.01607 | $0.01607 |
| Sonnet 5 | $0.00643 | $0.00643 |
| Haiku 4.5 | $0.00321 | $0.00321 |
Grade A, and why
rossum-agents AGENTS.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 6d 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 — 254 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Development Guidelines
Goal: Maintain code quality, consistency, and documentation across rossum-agents packages (rossum-mcp, rossum-agent, rossum-agent-client).
Critical Constraints
- No auto-commits - Only
git commit/git pushwhen explicitly instructed - Simplicity first - Design the simplest solution that works. Fewer abstractions, fewer indirections, fewer layers. If a reader needs to jump through hoops to understand the code, it's too complex.
- YAGNI - Don't add functionality until needed. Remove unused code proactively.
- Tests required - New features and bug fixes must include tests
- Docs in sync - Tool changes require documentation updates
- Changelog PR references - When adding changelog entries, include the PR hyperlink (e.g.
[#123](https://github.com/rossumai/rossum-agents/pull/123)) if available
Commands
| Task | Command |
|---|---|
| Setup | uv sync or uv pip install -e . |
| Server | rossum-mcp (installed) or python -m rossum_mcp.server (dev) |
| Tests | pytest or pytest path/to/test.py |
| Lint | pre-commit run --all-files |
| TUI lint | cd rossum-agent-tui && npm run lint && npm run format:check && npm run typecheck |
Architecture
- rossum-mcp: FastMCP server in
rossum_mcp/server.py; tools registered fromrossum_mcp/tools/modules - rossum-agent: AI agent with system prompt in
rossum_agent/system_prompt.py, skills inrossum_agent/skills/ - rossum-agent-tui: Development test-bed TUI for rossum-agent. Not production code — no tests required. Always use
/ink-tui-best-practicesskill when working on this package. - New skills: Create
rossum_agent/skills/<slug>.md— auto-discovered bySkillRegistry
Prompt Engineering (rossum-agent)
rossum-agent uses Opus 4.6 - optimize prompts in rossum_agent/system_prompt.py and rossum_agent/skills/ accordingly:
| Principle | Implementation |
|---|---|
| Goals over procedures | "Goal: Deploy safely" not step-by-step instructions |
| Constraints over explanations | "Never mix credentials" - Opus infers consequences |
| Tables for structure | More token-efficient than prose lists |
| No redundancy | Don't explain what Opus can infer |
| Facts not warnings | State rules directly, skip "IMPORTANT" preambles |
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.
- 6d ago First seen · 254 lines · 3,215 tokens per session scan A ba7604efe707
rossum-agents AGENTS.md is an instructions file published in the GitHub repository rossumai/rossum-agents (11 stars, last pushed 6d ago), licensed MIT. It adds 3,215 tokens to every session, about $0.0161 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).
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.
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
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.
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.
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.