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/joshidikshant/loopback/gemini-mdgit clone --depth 1 https://github.com/joshidikshant/loopbackWhat 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 | $0.00021 | $0.00021 |
| Opus 5 | $0.00010 | $0.00010 |
| Sonnet 5 | $0.00004 | $0.00004 |
| Haiku 4.5 | $0.00002 | $0.00002 |
Grade C, and why
loopback GEMINI.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 yesterday.
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.
<!-- Cross-agent instructions live in AGENTS.md (canonical); imported below. --> This is a copy
100% identical to loopback CLAUDE.md — 0 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
@AGENTS.md
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.
- yesterday First seen · 4 lines · 21 tokens per session scan C c3d4ad2ee720
loopback GEMINI.md is an instructions file published in the GitHub repository joshidikshant/loopback (0 stars, last pushed 1mo ago), licensed MIT. It adds 21 tokens to every session, about $0.0001 per session on Opus 5. A static security scan graded it C with 1 finding (hidden instructions). It is 100% identical to loopback CLAUDE.md, differing in 0 lines, and is treated as a copy.
Other instructions, from other repositories
gitpin AGENTS.md
AGENTS.md instructions for shmindmaster/gitpin, covering agents.md - gitpin, mission, knowledge authority, start here and architecture.
agent-harness-skills AGENTS.md
Instructions for yfge/agent-harness-skills, covering agent harness skills - repository instructions, purpose, rules, validation and commit discipline.
agent-harness-skills GEMINI.md
Instructions for yfge/agent-harness-skills: This extension provides reusable skills for repository harness design.
gitpin CLAUDE.md
Claude Code instructions for shmindmaster/gitpin, a project described as: Require exact PR evidence before agent-authored changes merge. Local evidence MCP + base-trusted gate.
matt-skills-with-to-goal CLAUDE.md
Instructions for tt-a1i/matt-skills-with-to-goal: Skills are organized into bucket folders under skills/.
coral CLAUDE.md
Instructions for cdknorow/coral, covering claude.md - coral go, mission, testing, go unit tests and legacy parity tools (historical reference).