Borrowing it
Nothing to install: this file belongs to codespar/codespar-core. 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/codespar/codespar-core/main/CLAUDE.mdgit clone --depth 1 https://github.com/codespar/codespar-coreWrote 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/codespar/codespar-core/claude-md)<a href="https://agentmods.dev/instructions/codespar/codespar-core/claude-md"><img src="https://agentmods.dev/badge/instructions/codespar/codespar-core/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/codespar/codespar-core/claude-md"><img src="https://agentmods.dev/badge/instructions/codespar/codespar-core/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 | $0.02042 | $0.02042 |
| Opus 5.5 | $0.00817 | $0.00817 |
| Sonnet 5.5 | $0.00408 | $0.00408 |
| Haiku 4.5 | $0.00204 | $0.00204 |
Grade A, and why
codespar-core 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 1mo 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 — 172 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CodeSpar Core — Project Instructions
What this repo is
The public, MIT-licensed SDK layer of CodeSpar: the TypeScript
@codespar/sdk npm package, the codespar Python package on PyPI,
and the framework adapters that wrap them (Vercel AI SDK, Claude Agent
SDK, OpenAI Agents SDK, MCP, CLI). Everything here is a client over
the CodeSpar API (default endpoint api.codespar.dev); the same SDK
also runs against a self-hosted runtime — baseUrl is a configuration
change.
Post-pivot (April 2026), CodeSpar is commerce infrastructure for AI agents in Latin America. These SDKs encode the wire contract that lets developers ship commerce agents (Pix + NF-e + WhatsApp + PSPs) without rebuilding the plumbing. Read the project VISION for the strategic context.
Authoritative context
- Strategy: read the project VISION before making strategic decisions.
- Wire contract: every SDK method here maps 1:1 to a backend route. Keep the TS types, the Python package, and the backend in lockstep — drift between SDKs is the loudest way to break trust.
- Current SDK shape:
CodeSpar.create(userId, { preset, servers, manageConnections, projectId, metadata })returns aSessionexposingtools,execute,proxyExecute,send,sendStream,authorize,connections,close.
Language
- Code, comments, file names, docs: English
- Conversation with user: Portuguese
Repository Map
| Repo | Role |
|---|---|
codespar-core (this repo, public MIT) |
SDK + adapters (TS + Python) |
codespar/codespar (public, MIT) |
Self-hostable runtime + channel adapters |
codespar/mcp-dev-latam (public, MIT) |
LATAM MCP server catalog |
A private managed tier serves the same session contract.
Package Inventory (monorepo under packages/)
core/→@codespar/sdk— canonical client. Sessions, managed auth, tool execution, Complete Loop.python/→codesparon PyPI (v0.1.1+). Same surface, sync + async flavours. Published via.github/workflows/publish-python.ymlusing PyPI trusted publishing (OIDC).types/→@codespar/types. Zero-dependencySessionBase/Sessioninterface hierarchy + conformance tests. Shared contract between the open-source runtime and the managed backend.managed-agents-adapter/→@codespar/managed-agents-adapter. RunsSessionBasetools against Anthropic Managed Agents sessions.vercel//claude//openai/— framework adapters.mcp/→@codespar/mcp. Emits config files for Claude Desktop, Cursor, VS Code clients pointing at a session's MCP endpoint.cli/→@codespar/cli. Auth + execute + session + scaffold commands. Entrycodespar-cli.
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.
- 1mo ago First seen · 172 lines · 2,042 tokens per session scan A 70658a60de3e
codespar-core CLAUDE.md is an instructions file published in the GitHub repository codespar/codespar-core (2 stars, last pushed today), licensed MIT. It adds 2,042 tokens to every session, about $0.0082 per session on Opus 5.5. 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
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).
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.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
vscode model-prompts.instructions.md
Model-specific prompt authoring and registry guidelines.