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/astonish/agents-mdgit clone --depth 1 https://github.com/SAP/astonishWhat 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 | $0.02347 | $0.02347 |
| Opus 5 | $0.01174 | $0.01174 |
| Sonnet 5 | $0.00469 | $0.00469 |
| Haiku 4.5 | $0.00235 | $0.00235 |
Grade A, and why
astonish 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 3d 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 — 137 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project overview
Astonish is an AI-agent platform distributed as one Go binary. It supports a local coding TUI, a remote multi-tenant chat/platform, HTTP/SSE APIs, reusable flows, tools/MCP, memory, browser automation, fleet orchestration, and isolated execution through Incus, Kubernetes, or OpenShell backends. The Studio UI is a React SPA embedded into the Go binary.
The repository is primarily:
- Go 1.26 (
go.mod, toolchaingo1.26.1) for the CLI, agent runtime, API, storage, TUI, and sandbox backends. - React 19 + TypeScript/legacy JSX + Vite + Tailwind CSS 4 under
web/. - Ent for scoped persistence, with SQLite for personal/development use and PostgreSQL for the multi-tenant platform.
Before changing a subsystem, read the nearest nested AGENTS.md; those files contain stricter subsystem-specific contracts and override this root guide.
Repository map
main.go,cmd/astonish/— binary entry point and CLI dispatch. Commands should parse arguments and delegate; keep business logic inpkg/. Preserve local/remote command gating. Bareastonishlaunches local code mode in a TTY.pkg/agent/— LLM-driven agent loop, prompt construction, tool execution, compaction, delegation, and approvals.pkg/api/— platform/Studio HTTP handlers, authentication, SSE chat/fleet streams, and orchestration wiring.pkg/launcher/— composition roots for local code TUI, remote chat TUI, and server/daemon launch paths.pkg/tui/,pkg/ui/— Bubble Tea terminal clients and reusable terminal rendering.pkg/tools/,pkg/browser/,pkg/codeintel/— built-in tools, CDP browser automation, and source-code intelligence.pkg/provider/,pkg/mcp/,pkg/skills/— model providers, MCP integration, and skill loading.pkg/config/— configuration loading, defaults, and environment overrides.pkg/store/— storage interfaces and implementations/routing; tenant scope is a core invariant.pkg/memory/,pkg/session/,pkg/fleet/,pkg/drill/,pkg/channels/— major domain subsystems.pkg/scheduler/— scheduled-job registration and execution.web/src/api/,web/src/components/chat/— Studio transport contracts and chat rendering/interaction guidance.pkg/sandbox/— backend-neutral sandbox contracts plus Incus/Kubernetes/OpenShell implementations.Backendimplementations must be concurrency-safe and lifecycle methods are intentionally idempotent.ent/{platform,org,team,personal}/— four persistence scopes. Onlyschema/*.goandgenerate.goare normally hand-edited; the remaining Ent files are generated.web/src/— Studio SPA. Entry points aremain.tsxandApp.tsx;api/contains REST/SSE clients andcomponents/contains UI.tests/e2e/,tests/e2eboot/,tests/scenarios/— tagged E2E suites, shared bootstrap harness, and scenario catalogs/reporters.docs/architecture/— authoritative design documents. Update the relevant document when changing a documented protocol or invariant.proto/,deploy/,docker/— protocol definitions, deployment assets, and container images.
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.
- 3d ago First seen · 137 lines · 2,347 tokens per session scan A 52a7c449222a
astonish AGENTS.md is an instructions file published in the GitHub repository SAP/astonish (20 stars, last pushed 3d ago), licensed Apache-2.0. It adds 2,347 tokens to every session, about $0.0117 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).
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.
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.
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.
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).
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.