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/amittamari/hop/agents-mdgit clone --depth 1 https://github.com/amittamari/hopWrote 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/amittamari/hop/agents-md)<a href="https://agentmods.dev/instructions/amittamari/hop/agents-md"><img src="https://agentmods.dev/badge/instructions/amittamari/hop/agents-md.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 | $0.00689 | $0.00689 |
| Opus 5 | $0.00345 | $0.00345 |
| Sonnet 5 | $0.00138 | $0.00138 |
| Haiku 4.5 | $0.00069 | $0.00069 |
Grade A, and why
hop 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 5d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Map
This file is the short entry point for coding agents. Keep it small. Durable
project knowledge belongs in docs/.
Start Here
- Project contract:
docs/PROJECT.md - Architecture map:
docs/ARCHITECTURE.md - User-facing usage:
README.md
What This Repo Builds
hop is a Rust CLI/TUI that indexes Claude Code and Codex session JSONL files,
searches them with Tantivy, previews a cleaned transcript, and exec-resumes the
selected session in the original working directory.
Working Rules
- Read
docs/RUST_GUIDELINES.mdbefore starting any implementation work. - Prefer the existing module boundaries over introducing new framework shape.
- Prefer files under ~500 lines. Crossing it on a file you're editing is a signal
to split by responsibility — not a hard limit. If a file is legitimately over
(e.g. dominated by colocated
#[cfg(test)]tests), add a one-line note near the top explaining why, and move on. Don't split modules purely to satisfy the count. - Keep
main.rsas orchestration only when possible; reusable behavior belongs in library modules. - Parse external data at adapter boundaries into
coretypes before indexing or rendering. - Keep agent-specific knowledge inside its adapter (
B-011): format quirks, magic field values, and per-agent judgments belong inadapters/<agent>.rs. Generic layers (engine,core,index,tui) must not name an agent-specific literal oradapters::<agent>::…symbol — reach adapters only through theAdaptertrait. When a generic layer needs a per-agent decision, add an agent-agnostic trait method with a safe default and override it in the adapter. - Keep the TUI responsive: no network calls, large scans, or broad filesystem work in the render path.
- Preserve resume behavior: restore the terminal before
exec, thenchdirand replace the process with the agent CLI. - Update documentation when changing architecture, user-visible behavior, or agent-facing workflows.
- Never write absolute local working-directory paths (e.g.
/Users/<name>/...or a personal~/workspaces/...layout) into committed files. Reference repos and files by their repo-relative path, well-known data dirs (~/.codex,~/.claude), or a neutral description like "a local checkout".
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.
- 5d ago First seen · 66 lines · 689 tokens per session scan A 13f44de242a7
hop AGENTS.md is an instructions file published in the GitHub repository amittamari/hop (5 stars, last pushed 7d ago), licensed MIT. It adds 689 tokens to every session, about $0.0034 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
coding-agent-fabric CLAUDE.md
Claude Code instructions for yu-iskw/coding-agent-fabric, covering typescript monorepo - claude code memory, project overview, quick commands, code style and testing.
skills AGENTS.md
AGENTS.md instructions for michaelshimeles/skills, covering agent workflow, workflow, writing for humans, multi-agent rules and completing a task.
pixeltamer-gpt-image-skill CLAUDE.md
Instructions for gabelul/pixeltamer-gpt-image-skill, covering claude.md — pixeltamer, what this is, architecture, how the skill works and the two backends.
codmate AGENTS.md
Instructions for loocor/codmate, a project described as: CodMate is a macOS SwiftUI app for managing CLI AI sessions: browse, search, organize, resume, and review work produced by Codex, Claude Code, and Gemini CLI. It focuses on speed, a compact three-column UI, and “ship it” workflows like Project Review (Git…
gh-stars-classifier-skill AGENTS.md
Instructions for catuscio/gh-stars-classifier-skill, covering github stars classifier — agent workflow, when to invoke, prerequisites (check first, fail fast), root resolver (run once, before any phase) and workflow.
coding-agent-safety-gate AGENTS.md
Instructions for ASER-ho/coding-agent-safety-gate, covering agents / 代理规则, 仓库类型 / repository type and ai 代理规则 / rules for ai coding agents.