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/sap-samples/cap-agentic-engineered/agents-mdgit clone --depth 1 https://github.com/SAP-samples/cap-agentic-engineeredWhat 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 | $0.01133 | $0.01133 |
| Opus 5 | $0.00566 | $0.00566 |
| Sonnet 5 | $0.00227 | $0.00227 |
| Haiku 4.5 | $0.00113 | $0.00113 |
Grade C, and why
cap-agentic-engineered AGENTS.md scanned grade C with 2 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.
Downloads and executes remote codehighSupply chain
curl | sh runs whatever the server returns today, which is not necessarily what it returned when this was reviewed.
- Never use `curl | bash`, `npx`, `pnpm dlx`, `uvx`, `pipx`, `cargo install`, `go install`, or any remote install one-liner without an exact pinned version and explicit approval Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
- Never use `curl | bash`, `npx`, `pnpm dlx`, `uvx`, `pipx`, `cargo install`, `go install`, or any remote install one-liner without an exact pinned version and explicit approval How it starts
The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Conversational Style
- Keep answers short and concise
- No emojis in commits, PR comments, or code
- Technical prose only
- No fluff or filler text
Code Quality
- No
anytypes unless absolutely necessary - Check node_modules for external API type definitions instead of guessing
- NEVER use inline imports - no
await import("./foo.js"), noimport("pkg").Typein type positions, no dynamic imports for types. Always use standard top-level imports. - NEVER remove or downgrade code to fix type errors from outdated dependencies; upgrade the dependency instead
- Always ask before removing functionality or code that appears to be intentional
- Do not preserve backward compatibility unless the user explicitly asks for it
- Never hardcode key checks with, eg.
matchesKey(keyData, "ctrl+x"). All keybindings must be configurable. Add default to matching object (DEFAULT_EDITOR_KEYBINDINGSorDEFAULT_APP_KEYBINDINGS)
Commands
- After code changes (not documentation changes):
npm run check(get full output, no tail). Fix all errors, warnings, and infos before committing. - Note:
npm run checkdoes not run tests. - NEVER run:
npm run dev,npm run build,npm test - Only run specific tests if user instructs:
npx tsx ../../node_modules/vitest/dist/cli.js --run test/specific.test.ts - Run tests from the package root, not the repo root.
- If you create or modify a test file, you MUST run that test file and iterate until it passes.
- When writing tests, run them, identify issues in either the test or implementation, and iterate until fixed.
- For
packages/coding-agent/test/suite/, usetest/suite/harness.tsplus the faux provider. Do not use real provider APIs, real API keys, or paid tokens. - Put issue-specific regressions under
packages/coding-agent/test/suite/regressions/and name them<issue-number>-<short-slug>.test.ts. - NEVER commit unless user asks
Development Rules
MCP Servers: Query Before Writing SAP Code
Before writing, modifying, or fixing any SAP-specific code, query the relevant MCP server. Do not rely on training knowledge alone. If MCP guidance conflicts with general knowledge, follow MCP.
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 · 73 lines · 1,133 tokens per session scan C 5101e69d8232
cap-agentic-engineered AGENTS.md is an instructions file published in the GitHub repository SAP-samples/cap-agentic-engineered (12 stars, last pushed 3mo ago), licensed Apache-2.0. It adds 1,133 tokens to every session, about $0.0057 per session on Opus 5. A static security scan graded it C with 2 findings (downloads and executes remote code, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other instructions, from other repositories
ox AGENTS.md
Instructions for sageox/ox, covering human attention is the scarcest resource, what is ox?, quick start, terminology and required reviews.
turbo-flow CLAUDE.md
Claude Code instructions for marcuspat/turbo-flow, covering claude.md — turbo flow, what this repo is, key files and conventions.
alignfirst AGENTS.md
Instructions for paleo/alignfirst, covering repository guidelines, tooling, packages, docmap - seek documentation and workspaces.
tauri-agent-tools AGENTS.md
Instructions for cesarandreslopez/tauri-agent-tools, covering tauri-agent-tools, agent skills and quick reference.
agent-skills AGENTS.md
Instructions for a-tokyo/agent-skills, covering agents.md, project overview, repo structure (monorepo), setup & commands and install / use a skill (consumer side).
aiworkspace AGENTS.md
Instructions for a-tokyo/aiworkspace, covering ai workspace, structure, key commands, conventions and code quality.