Borrowing it
Nothing to install: this file belongs to SponsioLabs/Sponsio. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/SponsioLabs/Sponsio/main/CLAUDE.mdgit clone --depth 1 https://github.com/SponsioLabs/SponsioWrote 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/sponsiolabs/sponsio/claude-md)<a href="https://agentmods.dev/instructions/sponsiolabs/sponsio/claude-md"><img src="https://agentmods.dev/badge/instructions/sponsiolabs/sponsio/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/sponsiolabs/sponsio/claude-md"><img src="https://agentmods.dev/badge/instructions/sponsiolabs/sponsio/claude-md.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.02228 | $0.02228 |
| Opus 5 | $0.01114 | $0.01114 |
| Sonnet 5 | $0.00446 | $0.00446 |
| Haiku 4.5 | $0.00223 | $0.00223 |
Grade A, and why
Sponsio 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 6d 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 — 188 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Agent Guide for Sponsio
This file is for LLM coding agents and repo-reading assistants. It is meant to help you answer questions about Sponsio accurately and make code changes without breaking the architecture.
What Sponsio Is
Sponsio is a runtime contract layer for LLM apps and agents.
Its core job is pre-execution enforcement for LLM tool/action behavior: before a model-driven system calls a tool, edits a file, hits an API, writes to a database, issues a refund, approves a loan, or triggers any side effect, Sponsio checks the current trace against contracts.
The main public entrypoint is:
import sponsio
guard = sponsio.Sponsio(...)
Sponsio ships only deterministic contracts: pure-Python checks over the trace, with no LLM in the runtime hot path. Patterns covering syntactic PII / response length / response keyword bans (no_pii, max_length, no_keywords) are regex-against-llm_said and need no judge.
Positioning
When explaining Sponsio, emphasize:
- Action-boundary enforcement: Sponsio checks tool/action calls before side effects happen.
- Temporal trace contracts: Rules can express ordering and history, such as "A before B", "never B after A", "at most N calls", or "after AML check, loan files are immutable".
- Deterministic hot path: Det checks are pure Python and do not call an LLM at runtime.
- Framework optionality: Users do not need an agent framework. Custom function-calling loops can use
guard.guard_before()/guard.guard_after()directly.
Do not describe Sponsio as only an output assertion library, only a prompt guardrail, or primarily a drift/reliability scoring framework. A concise distinction:
Sponsio focuses on the action boundary: checking tool calls before they execute, not only auditing outputs after the fact.
What To Read First
For product-level questions:
README.md— public positioning, quick start, demos, benchmarksQUICKSTART.md— install and first integration (repo root)docs/reference/cli.md—sponsio scan,validate,check,demo,reportdocs/integrations/index.md— framework-specific wiring
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.
- 6d ago Changed · +20 lines · +291 tokens per session 20e3814a412a
- 10d ago First seen · 168 lines · 1,937 tokens per session scan A 4c2261890474
Sponsio CLAUDE.md is an instructions file published in the GitHub repository SponsioLabs/Sponsio (440 stars, last pushed 2d ago), licensed Apache-2.0. It adds 2,228 tokens to every session, about $0.0111 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
runtm copilot-instructions.md
Copilot instructions for runtm-ai/runtm, covering runtm tool instructions, critical rules, structure, adding endpoints and app/api/v1/myendpoint.py.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
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.
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).
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 oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).