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/beita6969/scienceclaw/copilotgit clone --depth 1 https://github.com/beita6969/ScienceClawWrote 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/beita6969/scienceclaw/copilot)<a href="https://agentmods.dev/instructions/beita6969/scienceclaw/copilot"><img src="https://agentmods.dev/badge/instructions/beita6969/scienceclaw/copilot.svg" alt="Measured on agentmods" 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 | $0.00574 | $0.00574 |
| Opus 5 | $0.00287 | $0.00287 |
| Sonnet 5 | $0.00115 | $0.00115 |
| Haiku 4.5 | $0.00057 | $0.00057 |
Grade A, and why
ScienceClaw copilot.instructions.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 4d 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.
Copies of this mod
3 near-identical copies found in the catalogue:
- dglabs-deepclaw copilot.instructions.md — 100% identical, 0 lines differ
- openclaw-cn copilot.instructions.md — 100% identical, 0 lines differ
- openclaw-termux copilot.instructions.md — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.
OpenClaw Codebase Patterns
Always reuse existing code - no redundancy!
Tech Stack
- Runtime: Node 22+ (Bun also supported for dev/scripts)
- Language: TypeScript (ESM, strict mode)
- Package Manager: pnpm (keep
pnpm-lock.yamlin sync) - Lint/Format: Oxlint, Oxfmt (
pnpm check) - Tests: Vitest with V8 coverage
- CLI Framework: Commander + clack/prompts
- Build: tsdown (outputs to
dist/)
Anti-Redundancy Rules
- Avoid files that just re-export from another file. Import directly from the original source.
- If a function already exists, import it - do NOT create a duplicate in another file.
- Before creating any formatter, utility, or helper, search for existing implementations first.
Source of Truth Locations
Formatting Utilities (src/infra/)
- Time formatting:
src\infra\format-time
NEVER create local formatAge, formatDuration, formatElapsedTime functions - import from centralized modules.
Terminal Output (src/terminal/)
- Tables:
src/terminal/table.ts(renderTable) - Themes/colors:
src/terminal/theme.ts(theme.success,theme.muted, etc.) - Progress:
src/cli/progress.ts(spinners, progress bars)
CLI Patterns
- CLI option wiring:
src/cli/ - Commands:
src/commands/ - Dependency injection via
createDefaultDeps
Import Conventions
- Use
.jsextension for cross-package imports (ESM) - Direct imports only - no re-export wrapper files
- Types:
import type { X }for type-only imports
Code Quality
- TypeScript (ESM), strict typing, avoid
any - Keep files under ~700 LOC - extract helpers when larger
- Colocated tests:
*.test.tsnext to source files - Run
pnpm checkbefore commits (lint + format) - Run
pnpm tsgofor type checking
Stack & Commands
- Package manager: pnpm (
pnpm install) - Dev:
pnpm openclaw ...orpnpm dev - Type-check:
pnpm tsgo - Lint/format:
pnpm check - Tests:
pnpm test - Build:
pnpm build
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.
- 4d ago First seen · 65 lines · 574 tokens per session scan A 1a66e12d7b35
ScienceClaw copilot.instructions.md is an instructions file published in the GitHub repository beita6969/ScienceClaw (891 stars, last pushed 2mo ago), licensed MIT. It adds 574 tokens to every session, about $0.0029 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
biomcp AGENTS.md
AGENTS.md instructions for genomoncology/biomcp, covering agents.md — biomcp, packaged agent guide, repository contract shape, contract quick reference and gates.
openrouter-mcp-multimodal AGENTS.md
AGENTS.md instructions for stabgan/openrouter-mcp-multimodal, covering agent instructions, before you ship, releasing (read this before publishing), short version and version files (must all match package.json).
tpu_performance_autoresearch_wiki AGENTS.md
Instructions for vlasenkoalexey/tpu_performance_autoresearch_wiki, covering codex instructions, compatibility, operating rules and codex translation notes.
claude-code-zero CLAUDE.md
Instructions for LeeJuOh/claude-code-zero, covering claude.md and map.
eve-whatsapp-group-agent AGENTS.md
Instructions for mblode/eve-whatsapp-group-agent, covering eve-whatsapp-group-agent, make it yours, writing a tool and gotchas.
anki-mcp-server CLAUDE.md
Claude Code instructions for nailuoGG/anki-mcp-server, covering claude.md, repository overview, development commands, build & development and install dependencies.