Borrowing it
Nothing to install: this file belongs to a-attia/scicomp-research-skills. 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/a-attia/scicomp-research-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/a-attia/scicomp-research-skillsWrote 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/a-attia/scicomp-research-skills/agents-md)<a href="https://agentmods.dev/instructions/a-attia/scicomp-research-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/a-attia/scicomp-research-skills/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/a-attia/scicomp-research-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/a-attia/scicomp-research-skills/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 | $0.07960 | $0.07960 |
| Opus 5 | $0.03980 | $0.03980 |
| Sonnet 5 | $0.01592 | $0.01592 |
| Haiku 4.5 | $0.00796 | $0.00796 |
Grade A, and why
scicomp-research-skills 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 10d 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 — 650 lines — stays where its author put it; the contents beside it link to each section on GitHub.
scicomp-research-skills / AGENTS.md
You are reading the root AGENTS.md of a shared agent-skills
repository. Read this file first before doing anything else here or in
any project that references it.
This file follows the agents.md open standard.
Agent clients that look for other filenames (e.g. CLAUDE.md) read this
same content via symlinks created by bin/install.sh.
PROVISIONAL FRAMEWORK (as of 2026-05-14): some skill content here is well-grounded (research-paper-writing, literature-survey, paper-skeleton template); other skill content is informed prediction from prior-art audits but has not yet been validated by any real research-project session. When a rule feels speculative or doesn't quite fit the situation, surface that to the user explicitly + append an entry to the project's
notes/agent_feedback.md(peragent-resource-discipline/references/persistent-memory.md). SeeSTATUS.mdat the repo root for the honest map of what is tested vs speculative.
1. What this repository is
This repository holds agent skills and workflow templates for research in scientific computing -- covering both research papers (drafts, literature surveys, reviewer responses) and research software (libraries, codes, reproducibility infrastructure) in domains such as computational PDEs, inverse problems, optimal experimental design, uncertainty quantification, optimisation, and scientific machine learning.
The repository exists so that:
- Conventions are defined once and inherited everywhere. A
per-project
AGENTS.mdis short and project-specific; the generic conventions live here as skills loaded on demand. - The same conventions work across multiple agent clients -- OpenCode, Claude Code, Codex, Cursor, Aider, Gemini CLI, etc. Any client that reads markdown can consume this repository.
- The same conventions work across multiple machines. A canonical
checkout at
~/.scicomp-research-skills/on each machine is refreshed viagit pull; one source of truth. - Updates are versioned. Every change to a convention or skill is a
commit with a message;
git logshows when and why.
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.
- 10d ago First seen · 650 lines · 7,960 tokens per session scan A 3a214d4856c8
scicomp-research-skills AGENTS.md is an instructions file published in the GitHub repository a-attia/scicomp-research-skills (11 stars, last pushed 6d ago), licensed MIT. It adds 7,960 tokens to every session, about $0.0398 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
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.
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 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).
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).
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.
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.