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/ariestar/sivtr/claude-mdgit clone --depth 1 https://github.com/Ariestar/sivtrWrote 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/ariestar/sivtr/claude-md)<a href="https://agentmods.dev/instructions/ariestar/sivtr/claude-md"><img src="https://agentmods.dev/badge/instructions/ariestar/sivtr/claude-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 | $0.01902 | $0.01902 |
| Opus 5 | $0.00951 | $0.00951 |
| Sonnet 5 | $0.00380 | $0.00380 |
| Haiku 4.5 | $0.00190 | $0.00190 |
Grade A, and why
sivtr CLAUDE.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 — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
sivtr is a terminal output workspace that captures, browses, searches, and reuses terminal command output and AI coding assistant sessions. Agent providers are registry-driven (Codex, Claude Code, Cursor, OpenCode, OpenClaw, Grok, Hermes, Pi, …) and four shells (Bash, Zsh, PowerShell, Nushell). Cross-device remote memory uses a local daemon with Share/Grant/Mount over encrypted iroh transport.
Architecture: CLI binary (src/) wrapping a core library (crates/sivtr-core/). Clap-based subcommands for copy, search, show, work, filter, var, nav, zoom, init, diff, hotkey, doctor, serve, share, group, remote, peer, and workspace. TUI mode for browse/search views.
Development Commands
cargo build # debug
cargo test --workspace # all tests
cargo fmt --all -- --check # format check
cargo clippy --workspace --all-targets -- -D warnings # clippy (strict)
Pre-commit gate:
cargo fmt --all && cargo clippy --workspace --all-targets -- -D warnings && cargo test --workspace
Workspace Structure
crates/sivtr-core/src/ ← Core library (no CLI deps)
agents/ ← AgentProvider registry + per-provider parsers
mod.rs / model.rs / jsonl.rs / sqlite.rs
claude.rs / codex.rs / cursor.rs / grok.rs / hermes.rs / openclaw.rs / opencode.rs / pi.rs
record/
model.rs ← WorkRecord, WorkPart, WorkTime (canonical model)
refs.rs ← WorkRef parsing (local body + origin:body remote form)
index.rs ← Record indexing and lookup
query/ ← Workspace record/source loading
search/ ← Filter/Searcher pipeline, BM25 ranking (types.rs, filter.rs, bm25.rs, eval.rs)
workspace.rs ← Workspace resolution (git root → sessions), data_dir()
workset.rs ← WorkSet / WorkSelection* canonical selection model
config/ ← SivtrConfig, serde TOML
history/ ← SQLite command history
session.rs ← Session log reading
time.rs ← Timestamp normalization
src/ ← CLI binary
main.rs ← Command routing
cli/
mod.rs ← Top-level Clap definitions (copy agents via registry external subcommand)
remote.rs ← serve/share/peer/remote/group/workspace Clap types
commands/
capture/ ← copy, pipe, run, init, flush, import, diff, clear, browse
memory/ ← search, filter, var, nav, zoom, show, work, workset
remote/ ← serve, share, mounts, peer, group, workspace
system/ ← config, doctor, history, hotkey, codex, migrate, version
remote/ ← Device daemon, identity, state, protocol, ipc
tui/ ← Terminal UI framework
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 · 140 lines · 1,902 tokens per session scan A 655c0898ec17
sivtr CLAUDE.md is an instructions file published in the GitHub repository Ariestar/sivtr (258 stars, last pushed today), licensed Apache-2.0. It adds 1,902 tokens to every session, about $0.0095 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 2026-08-30.
Other instructions, from other repositories
openpencil CLAUDE.md
Claude Code instructions for ZSeven-W/openpencil, covering claude.md, commands, architecture, code style and git commit convention.
intelligent-terminal rust.instructions.md
Concise Rust coding conventions for this repository.
intelligent-terminal rust-wta.instructions.md
File-scoped conventions for the WTA Rust crate.
bifrost AGENTS.md
AGENTS.md instructions for bifrost-proxy/bifrost, covering bifrost 项目开发规则, 执行心法, 执行模式与完成定义, 任务模式判定 and 变更类型与验证路由（先判定，后执行）.
anda AGENTS.md
AGENTS.md instructions for ldclabs/anda, covering agents.md, scope, repository shape, working rules and runtime boundaries.
Symbiont AGENTS.md
AGENTS.md instructions for ThirdKeyAI/Symbiont, covering symbiont — agent instructions, project structure, build and test, code style and commit guidelines.