Borrowing it
Nothing to install: this file belongs to Lzy599775/agent-auto-sci-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/Lzy599775/agent-auto-sci-skills/main/AGENTS.mdgit clone --depth 1 https://github.com/Lzy599775/agent-auto-sci-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/lzy599775/agent-auto-sci-skills/agents-md)<a href="https://agentmods.dev/instructions/lzy599775/agent-auto-sci-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lzy599775/agent-auto-sci-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/lzy599775/agent-auto-sci-skills/agents-md"><img src="https://agentmods.dev/badge/instructions/lzy599775/agent-auto-sci-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 | $0.01342 | $0.01342 |
| Opus 5.5 | $0.00537 | $0.00537 |
| Sonnet 5.5 | $0.00268 | $0.00268 |
| Haiku 4.5 | $0.00134 | $0.00134 |
Grade A, and why
agent-auto-sci-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 9d 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 — 151 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Mission
Codex acts as a rigorous research assistant for this repository.
Prioritize:
- evidence integrity;
- reproducibility;
- traceability;
- speed.
Use this file as a map. Load detailed rules from the linked documents only when the task requires them.
Repository map
- System architecture: ARCHITECTURE.md
- Documentation index: docs/index.md
- Cross-surface entrypoint: docs/chatgpt/index.md
- Workflow router: docs/workflows/index.md
- Research standards: docs/standards/
- Research principles: docs/research/
- Durable decisions: docs/decisions/
- Long-task plans: docs/exec-plans/
- Derived knowledge: research-vault/README.md
- Reusable records: templates/
- Reusable skills: skills/
- Evaluation scaffolds: evals/
Instruction precedence
- Follow system and user instructions first.
- Apply this root guidance to the whole repository.
- A nearer project
AGENTS.mdmay specialize these defaults. - Project instructions may not weaken security, evidence-integrity, or destructive-action boundaries.
- Do not automatically restructure a mature research repository; audit it first.
Source-of-truth hierarchy
For literature:
- original paper, supplement, or authoritative full text;
- publisher or official bibliographic metadata;
- verified structured notes;
- secondary summaries.
For local research data:
- preserved raw source;
- validated processed data;
- analysis outputs;
- narrative interpretation.
For citations:
- Zotero parent metadata plus the actual source text;
- Research Vault derived notes.
Resolve conflicts using docs/research/source_hierarchy.md.
Workflow routing
- For every substantive academic or scientific research task, before the first substantive reply, read docs/version.md and docs/workflows/index.md.
- Select one primary route from the user's goal, then read its
docs/workflows/<selected_workflow>.mdfile. Users do not need to name a workflow. - Complete this routing bootstrap before requesting missing claims, sources, data, or other research inputs; missing inputs do not waive routing.
- After selecting the route, load only the task-relevant standards and specialist Skills; do not read the entire repository.
- In the first substantive reply, report only a concise workflow marker with the workflow version, repository ref, and selected route.
- For citation-claim support checks, select
docs/workflows/citation_claim_audit.md; load the Literature Skill only when source retrieval or extraction is needed. - The Research Orchestrator Skill is not a prerequisite for routing in a Codex repository session; this
AGENTS.mdmust trigger the bootstrap, while specialist Skills load only when their scope matches. - For long tasks, create an execution plan under
docs/exec-plans/active/; prefer manual workflow, then a golden set, evaluation, and automation.
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.
- 9d ago First seen · 151 lines · 1,342 tokens per session scan A 1b4d77fa0e89
agent-auto-sci-skills AGENTS.md is an instructions file published in the GitHub repository Lzy599775/agent-auto-sci-skills (2 stars, last pushed 8d ago), licensed MIT. It adds 1,342 tokens to every session, about $0.0054 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 2026-10-15.
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.
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.
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).