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/piebald-ai/splitrail/agents-mdgit clone --depth 1 https://github.com/Piebald-AI/splitrailWhat 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 | $0.00359 | $0.00359 |
| Opus 5 | $0.00179 | $0.00179 |
| Sonnet 5 | $0.00072 | $0.00072 |
| Haiku 4.5 | $0.00036 | $0.00036 |
Grade A, and why
splitrail 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 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.
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.
What it actually says
Project Overview
Splitrail is a high-performance, cross-platform usage tracker for AI coding assistants (Claude Code, Copilot, Cline, Pi Agent, etc.). It analyzes local data files from these tools, aggregates usage statistics, and provides real-time TUI monitoring with optional cloud upload capabilities.
Architecture
Analyzer System
Pluggable architecture with the Analyzer trait. Registry in src/analyzer.rs, individual analyzers in src/analyzers/. Each analyzer discovers data sources, parses conversations, and normalizes to a common format.
Data Flow
- Discovery: Analyzers find data files using platform-specific paths (
src/analyzers/) - Parsing: Parse JSON/JSONL into normalized messages (
src/types.rs) - Deduplication: Hash-based dedup using global hash field
- Aggregation: Group by date, compute token counts, costs, file ops (
src/utils.rs) - Display: TUI renders daily stats + real-time updates (
src/tui.rs,src/watcher.rs)
Code Style
- Follow Rust 2024 edition conventions
- Use
anyhow::Resultfor error handling - Prefer
async/awaitover raw futures - Use
parking_lotlocks overstd::syncfor performance
Post-Change Verification
Run after code changes:
cargo build --quiet
cargo test --quiet
cargo clippy --quiet -- -D warnings
cargo doc --quiet
cargo fmt --all --quiet
Additional Context
Skills provide task-specific guidance. Use the skill tool to load one when needed - available skills are listed in its description.
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 · 40 lines · 359 tokens per session scan A 28d5e2fcc57b
splitrail AGENTS.md is an instructions file published in the GitHub repository Piebald-AI/splitrail (218 stars, last pushed 11d ago), licensed MIT. It adds 359 tokens to every session, about $0.0018 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
siteone-crawler CLAUDE.md
Instructions for janreges/siteone-crawler, covering claude.md, core working principles, setup after clone, build & test commands and quick run.
unbuilt.app AGENTS.md
Instructions for yavorsky/unbuilt.app, covering agents.md — unbuilt.app, project structure, how detection works, pattern interface and key types.
unbuilt.app CLAUDE.md
Instructions for yavorsky/unbuilt.app, a project described as: Free and Open Source technology detection tool.
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.