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/tx1207/hello-scholar/agents-mdgit clone --depth 1 https://github.com/Tx1207/hello-scholarWhat 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 | $0.02360 | $0.02360 |
| Opus 5 | $0.01180 | $0.01180 |
| Sonnet 5 | $0.00472 | $0.00472 |
| Haiku 4.5 | $0.00236 | $0.00236 |
Grade A, and why
hello-scholar 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 2d 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 — 131 lines — stays where its author put it; the contents beside it link to each section on GitHub.
hello-scholar Guide
Write code that will not need to be rewritten.
1. Read Before You Write
Read the relevant context fully and ground implementation choices in project facts.
- Before making changes, read each file that will be modified in full and use its complete context to determine the change boundary.
- Start from the current implementation: inspect relevant imports, configuration, callers, and tests to establish actual dependencies, established patterns, and behavioral constraints.
- Reuse confirmed project choices. When changing an existing pattern, library, or interface, explain the reason and impact with local facts.
- When available evidence cannot determine the implementation, identify the unresolved facts and ask the user for a decision or more information.
2. Think Before Coding
Turn assumptions, tradeoffs, and open questions that affect implementation into explicit decisions.
Before implementing:
- State an assumption and its impact when it affects behavior, files, records, or risk.
- When different interpretations would materially change behavior, describe the ambiguity and available decisions. When the impact is small, state the reasonable interpretation you adopt and proceed.
- Among approaches that meet the current request, choose the simpler one and explain why it is sufficient.
- Ask for a decision before editing when missing information makes a change high-risk or irreversible. For other unresolved facts, record the adopted assumption and how it will be verified.
3. Simplicity First
Bound work by current facts and confirmed requirements, and deliver the smallest implementation that can be verified and evolved.
- Every new behavior, abstraction, configuration option, extension point, or defensive branch must trace to a current requirement, known runtime condition, or established project pattern.
- Begin with the smallest implementation that can be verified end to end. Expand it only when the current implementation works and the additional capability is truly needed.
- Retain old names, paths, aliases, shims, or dual-track flows only when a named external contract requires compatibility. For breaking or cross-version upgrades, use one clean source of truth and eliminate parallel writes.
- When the change scope grows, reconsider whether it can be split into independent, verifiable deliveries. When scope or facts remain unclear, return to design to resolve them.
- Choose a structure that can sustain the current need over time. Design only for confirmed current requirements; when a new need becomes concrete, extend through an independent, verifiable change.
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.
- 2d ago First seen · 131 lines · 2,360 tokens per session scan A f13bdbcb0364
hello-scholar AGENTS.md is an instructions file published in the GitHub repository Tx1207/hello-scholar (5 stars, last pushed 21d ago), licensed MIT. It adds 2,360 tokens to every session, about $0.0118 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 2026-08-31.
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.