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/jjhbrams/project-amber/project-guidesgit clone --depth 1 https://github.com/JJHbrams/Project-AMBERWrote 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/jjhbrams/project-amber/project-guides)<a href="https://agentmods.dev/instructions/jjhbrams/project-amber/project-guides"><img src="https://agentmods.dev/badge/instructions/jjhbrams/project-amber/project-guides.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 | $0.00253 | $0.00253 |
| Opus 5 | $0.00127 | $0.00127 |
| Sonnet 5 | $0.00051 | $0.00051 |
| Haiku 4.5 | $0.00025 | $0.00025 |
Grade C, and why
Project-AMBER project-guides.instructions.md scanned grade C with 1 finding 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.
Hidden instructionshighPrompt injection
Directives inside HTML comments, invisible characters or bidirectional overrides are read by the model and not by the person reviewing the file.
<!-- Tip: Use /create-instructions in chat to generate content with agent assistance --> What it actually says
Provide project context and coding guidelines that AI should follow when generating code, answering questions, or reviewing changes.
Todo List 관리 지침
docs/todo/User Todo list.md와docs/todo/todo.md를 주기적으로 확인하고, 내용이 변경되었으면docs/todo/todo.md에 반영하여 갱신한다.- 사용자가 todo와 무관한 작업을 지시했을 때, 미결 항목이 있으면 작업 전후 한 줄로 remind 한다.
- 완료된 항목은 완료 후 7일이 지나면
todo.md에서 삭제한다.
커밋 지침
- 개발 repo 커밋 할 때는 change log 를 업데이트할 것
- 배포 repo 커밋할 때는 release note 를 업데이트할 것
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 · 20 lines · 253 tokens per session scan C 52f598c643e3
Project-AMBER project-guides.instructions.md is an instructions file published in the GitHub repository JJHbrams/Project-AMBER (2 stars, last pushed 9d ago), licensed MIT. It adds 253 tokens to every session, about $0.0013 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
mulch AGENTS.md
AGENTS.md instructions for jayminwest/mulch, covering agents.md, what this project is, tech stack at a glance, project layout and commands.
Dragon-Brain CLAUDE.md
Instructions for iikarus/Dragon-Brain, covering dragon brain — claude.md, the harness, audit remediation (april–may 2026, complete 2026-05-09), the lie this audit closed and the contract that matters now.
quota-tracker AGENTS.md
AGENTS.md instructions for Thomas97460/quota-tracker, covering agent guidelines — quota-tracker, commits, hard stops, code rules and workflow.
task-orchestrator CLAUDE.md
Instructions for jpicklyk/task-orchestrator, covering project: mcp task orchestrator, build commands, docker (most common), architecture and modes of operation.
SiftMarks AGENTS.md
Instructions for Lling0000/SiftMarks, covering siftmarks agent notes, project shape, commands, current caveats and working rules.
TokenPilot CLAUDE.md
Claude Code instructions for eowlsdh/TokenPilot, a project described as: Local-first macOS menu bar utility for AI coding-tool usage metadata.