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/uhop/console-toolkit/claude-mdgit clone --depth 1 https://github.com/uhop/console-toolkitWhat 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 | $0.00033 | $0.00033 |
| Opus 5 | $0.00016 | $0.00016 |
| Sonnet 5 | $0.00007 | $0.00007 |
| Haiku 4.5 | $0.00003 | $0.00003 |
Grade C, and why
console-toolkit CLAUDE.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 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.
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.
<!-- Claude Code project instructions — canonical source is AGENTS.md --> This is a copy
88% identical to console-toolkit copilot-instructions.md — 4 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
See AGENTS.md for all AI agent rules and project conventions.
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 · 4 lines · 33 tokens per session scan C 77d6935a15d9
console-toolkit CLAUDE.md is an instructions file published in the GitHub repository uhop/console-toolkit (10 stars, last pushed 1mo ago), licensed BSD-3-Clause. It adds 33 tokens to every session, about $0.0002 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). It is 88% identical to console-toolkit copilot-instructions.md, differing in 4 lines, and is treated as a copy.
Other instructions, from other repositories
microcharts AGENTS.md
Instructions for ganapativs/microcharts: Single source of truth: CLAUDE.md. All non-negotiables, stack picks, architecture map, catalog rules, quality bar, roadmap position, and session working rules live there — read it in full before any work. CONTRIBUTING.md covers what the project takes (bug fixes and fixes to…
microcharts CLAUDE.md
Instructions for ganapativs/microcharts, covering microcharts — contributor & agent guide, design principles, non-negotiables (violating any of these is a bug), not shipped (by design) and stack.
recharts AGENTS.md
Instructions for recharts/recharts: This is Recharts repository. Recharts is a React-based charting library. The goal is to provide a simple, declarative, and composable way to build charts. We value consistency, usability, and performance. Accessibility is important.
joint CLAUDE.md
Instructions for clientIO/joint, covering claude.md, project overview, common commands, install dependencies and build distribution files (runs grunt).
ShipSwift AGENTS.md
Instructions for signerlabs/ShipSwift, covering agents.md, project overview, directory structure, naming conventions and dependency rules.
VChart AGENTS.md
Instructions for VisActor/VChart, covering vchart 工程基准, 编码习惯, 文档规范 and 优先级.