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 skills/piebald-ai/splitrail/typesnpx skills add Piebald-AI/splitrail --skill typesgit 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 | $0.00028 | $0.00234 |
| Opus 5 | $0.00014 | $0.00117 |
| Sonnet 5 | $0.00006 | $0.00047 |
| Haiku 4.5 | $0.00003 | $0.00023 |
Grade A, and why
types 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
Key Types
Read src/types.rs for full definitions.
Core Types
-
ConversationMessage - Normalized message format across all analyzers. Contains application source, timestamp, hashes for deduplication, model info, token/cost stats, and role.
-
Stats - Comprehensive usage metrics for a single message including token counts, costs, file operations, todo tracking, and composition stats by file type.
-
DailyStats - Pre-aggregated stats per date with message counts, conversation counts, model breakdown, and embedded Stats.
-
Application - Enum identifying which AI coding tool a message came from.
-
MessageRole - User or Assistant.
Hashing Strategy
local_hash: Deduplication within a single analyzerglobal_hash: Deduplication on upload to Splitrail Cloud
Aggregation
Use crate::utils::aggregate_by_date() to group messages into daily stats. See src/utils.rs.
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 · 30 lines · 28 tokens per session scan A 18b9cb39844e
types is a skill published in the GitHub repository Piebald-AI/splitrail (218 stars, last pushed 11d ago), licensed MIT. It adds 28 tokens to every session and 234 once invoked, about $0.0001 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 skills, from other repositories
lint-js
Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).
feishu
Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.
interview
Ask one useful structured question at a time only when material product/implementation choices are genuinely missing; remember answers and produce a brief/spec. Discoverable facts should be investigated instead of asked.
test
Detect the project’s test stack, run the narrowest useful tests, create tests when authorized, and report coverage/gaps honestly.
verify
Exercise the real app/API/CLI and collect observable evidence; tests alone do not count as end-to-end verification.
pptx
Create/edit/inspect/verify slide decks and PPTX presentations.