Borrowing it
Nothing to install: this file belongs to Tenstu/Pass-LLM-with-LLM. 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/Tenstu/Pass-LLM-with-LLM/main/AGENTS.mdgit clone --depth 1 https://github.com/Tenstu/Pass-LLM-with-LLMWrote 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/tenstu/pass-llm-with-llm/agents-md)<a href="https://agentmods.dev/instructions/tenstu/pass-llm-with-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/tenstu/pass-llm-with-llm/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/tenstu/pass-llm-with-llm/agents-md"><img src="https://agentmods.dev/badge/instructions/tenstu/pass-llm-with-llm/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 | $0.01806 | $0.01806 |
| Opus 5 | $0.00903 | $0.00903 |
| Sonnet 5 | $0.00361 | $0.00361 |
| Haiku 4.5 | $0.00181 | $0.00181 |
Grade A, and why
Pass-LLM-with-LLM 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 — 153 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Project Contract
This repository is an execution harness for AI / algorithm written-exam preparation. It is not a general knowledge base and not a place for broad research unless the user explicitly asks.
Primary goal: maximize written-exam pass probability. Secondary goal: keep only the minimum useful interview-prep material for follow-up interviews.
Default focus can be adjusted per target, but the baseline is:
| Area | Default |
|---|---|
| Question types | Single choice, multi-select, programming |
| Math | Linear algebra, probability, calculus quick-score questions |
| AI focus | Transformer, GNN, diffusion models, LLM inference optimization |
| Common overlap | SFT / LoRA / RLHF, RAG, KV cache, Python OJ algorithms |
When tradeoffs appear, prioritize algorithm AC practice, then math / multiple-choice quick-score topics, then AI concept review, then project-expression polishing.
Harness Engineering Rules
Every session must preserve the minimum loop:
intake -> practice -> record -> review -> handoff
Keep files in their lane:
| Need | Source of Truth |
|---|---|
| Session bootstrap | START_HERE.md |
| Current target, last work, next action | HANDOFF.md |
| User-facing setup and directory guide | README.md |
| Detailed skill behavior | skills/ |
| Target-specific practice state | targets/{target}/ |
| Shared daily logs and optional MCP source | shared/ |
| Dev-only plans, roadmap, branch governance | docs/ |
Do not turn AGENTS.md into an architecture manual. Put durable explanations in README / docs, and put operational details in the relevant skill file.
Runtime Modes
The harness must continue even when enhanced tooling is unavailable.
| Mode | Condition | Persistence |
|---|---|---|
| Full MCP Mode | exam-memory MCP is callable and the repo is writable |
Markdown + MCP dual write |
| Local Markdown Mode | MCP / ChatMem / local indexes are unavailable but repo files are writable | HANDOFF.md, daily logs, mistake_log.md, round files |
| Stateless Lite Mode | repo is not writable, key files are missing, or the session can only continue in chat | return append blocks such as [MISTAKE_LOG_APPEND], [DAILY_PROBLEM_LOG_APPEND], [CHOICE_ROUND_SUMMARY], [HANDOFF_UPDATE] |
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 · 153 lines · 1,806 tokens per session scan A a1336c491bfe
Pass-LLM-with-LLM AGENTS.md is an instructions file published in the GitHub repository Tenstu/Pass-LLM-with-LLM (5 stars, last pushed 2mo ago), licensed MIT. It adds 1,806 tokens to every session, about $0.0090 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
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.
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.