Borrowing it
Nothing to install: this file belongs to AGI4Sci/SciForge. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/AGI4Sci/SciForge/main/AGENTS.mdgit clone --depth 1 https://github.com/AGI4Sci/SciForgeWrote 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/agi4sci/sciforge/agents-md)<a href="https://agentmods.dev/instructions/agi4sci/sciforge/agents-md"><img src="https://agentmods.dev/badge/instructions/agi4sci/sciforge/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/agi4sci/sciforge/agents-md"><img src="https://agentmods.dev/badge/instructions/agi4sci/sciforge/agents-md.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00553 | $0.00553 |
| Opus 5.5 | $0.00221 | $0.00221 |
| Sonnet 5.5 | $0.00111 | $0.00111 |
| Haiku 4.5 | $0.00055 | $0.00055 |
Grade A, and why
SciForge 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 22d 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 — 27 lines — stays where its author put it; the contents beside it link to each section on GitHub.
SciForge repository instructions
These are standing instructions for every Codex task in this repository, including work delegated to sub-agents. Apply them by default without requiring the user to repeat them.
Architecture principles
- Design every feature as a cohesive, independently ownable module with an explicit public contract. Keep domain implementation details out of the application core.
- A domain package is the unit of ownership, versioning, installation, and release. Its backend and UI belong to the same package and version, while main-process and renderer code use separate explicit entrypoints. UI is optional for backend-only domains.
- Discover installed domain packages through the standard manifest and generated composition path. Adding or removing a domain package must not require editing a central feature map, domain-ID switch, or domain-specific host configuration.
- The host may depend on generic SDK contracts and extension points only. Domain packages must not import host-private
src/main,src/renderer,src/shared,@shared, or@rendererimplementation paths. - Keep one canonical path for each capability, preview operation, state transition, and external write. Do not add parallel IPC, MCP, service, facade, registry, or fallback paths for the same behavior.
Change policy
- When legacy behavior or structure conflicts with the target architecture, delete it and implement the clean target design directly. Do not add compatibility aliases, forwarding layers, migration shims, deprecated branches, or dual registration unless the user explicitly requires compatibility.
- All changes must be general. Never add a hard-coded exception for a showcase, fixture, domain ID, MIME type, plugin, provider, or current package when the behavior belongs in a contract, registry, manifest, or package-owned contribution.
- Consolidate duplicated logic at the narrowest shared generic boundary. Remove redundant branches, unused exports, unreachable code, stale tests, and dependencies once their remaining references have been audited.
- Prefer the smallest design that completely satisfies the requirement. Avoid speculative abstraction, extra lifecycle layers, duplicated metadata, and configuration that has no current consumer.
- Preserve user-visible behavior unless the requested target explicitly changes it. Tests should exercise the canonical production path rather than compatibility or test-only bypasses.
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.
- 22d ago First seen · 27 lines · 553 tokens per session scan A 071b01641a55
SciForge AGENTS.md is an instructions file published in the GitHub repository AGI4Sci/SciForge (83 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 553 tokens to every session, about $0.0022 per session on Opus 5.5. 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 2026-10-02.
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
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 copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deepseek-harness AGENTS.md
AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.