skills CLAUDE.md

Repository instructions for tools that create, test, and debug CEL, a language for writing expressions evaluated against structured data.

In plain words
What is it for?
Use them to author or debug CEL expressions, inspect environments, run evaluations, build the CLI or MCP server, and run tests.
Why use it?
They explain the project layout and the commands needed to build, run, and test its Go, CLI, MCP, and Bazel components.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/cel-expr/skills/claude-md
Clone the repo
git clone --depth 1 https://github.com/cel-expr/skills
Per session 668 This file is loaded in full into every session.
When invoked 668 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.00668 $0.00668
Opus 5 $0.00334 $0.00334
Sonnet 5 $0.00134 $0.00134
Haiku 4.5 $0.00067 $0.00067

Measured yesterday against content hash 47fabe4ba717, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

skills 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 yesterday.

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.

CLAUDE.md · 73 lines

How it starts

The opening of the file, as written. The whole thing — 73 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Common Expression Language (CEL) Skills

This repository provides tools and skills to author, test, and debug Common Expression Language (CEL) expressions.

Project Structure & Architecture

  • cmd/cli: Unified CLI and MCP server entry point (cel-expr).
  • cmd/mcp: Standalone entry point for the Model Context Protocol (MCP) server (cel-expr-mcp).
  • internal/mcp: MCP server implementation, transport setup, and tool dispatch.
  • internal/tools: Internal implementation for environment loading, compilation, evaluation, coverage, and prompt generation.
  • skills/: Agent skills directory containing guidelines and workflows:
    • cel-authoring: Authoring, configuring, and testing expressions and JSON environment definitions.
    • cel-debugging: Diagnosing and resolving compilation and evaluation errors.

Build and Test Commands

Go CLI

  • Build unified CLI: go build ./cmd/cli
  • Build MCP server: go build ./cmd/mcp
  • Run tests: go test ./...
  • Run unified CLI: go run ./cmd/cli <compile|eval|env|prompt|mcp>
  • Run MCP server: go run ./cmd/mcp

Bazel

  • Build all targets: bazel build //...
  • Run all tests: bazel test //...

Provided Tools

The cel-expr-mcp MCP server provides the following tools for AI agents:

  • cel_create_environment: Defines the variables, functions, and types for a CEL expression environment.
  • cel_generate_prompt: Generates an authoring prompt for a CEL expression based on the configuration and requirement.
  • cel_compile: Compiles a CEL expression to validate syntax, correctness, and type checking against an environment definition.
  • cel_evaluate: Evaluates a compiled expression against provided test cases.

Startup Flags

The server accepts startup flags to tailor the tool experience:

  • -environment (alias -env): Path to a JSON file or JSON string containing the CEL environment configuration.
  • -file_descriptor_set (alias -file_descriptors): Path to a binary FileDescriptorSet file containing protobuf definitions referenced as types within an environment.

Read the full file on GitHub · 73 lines

Changes

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.

  1. yesterday First seen · 73 lines · 668 tokens per session scan A 47fabe4ba717

Subscribe to this mod's changes

skills CLAUDE.md is an instructions file published in the GitHub repository cel-expr/skills (2 stars, last pushed 5d ago), licensed Apache-2.0. It adds 668 tokens to every session, about $0.0033 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 2026-08-31.

Related

Other instructions, from other repositories

ai-toolkit AGENTS.md

Instructions for pipefy/ai-toolkit, covering repository guidelines, documentation map, project structure, import namespace migration: pipefysdk → pipefy and src/pipefysdk/init.py (transitional shim).

pipefy/ai-toolkit · 3,184 tokens

superpowers-reasonix AGENTS.md

Instructions for christopherarter/superpowers-reasonix, covering project guidance, skills — stop. load a skill before you act, red flags — these thoughts mean stop. you are rationalizing and priority.

christopherarter/superpowers-reasonix · 761 tokens

cognirepo CLAUDE.md

Instructions for ashlesh-t/cognirepo, covering claude.md, key rules, session start sequence (run in this order), behavioral confirmation rule and personas (cognirepo-402, cognirepo-403).

ashlesh-t/cognirepo · 2,241 tokens

ai-mind AGENTS.md

Instructions for HWYD/ai-mind, covering agents, version spec workspace continuity (mandatory), 项目定位, 事实来源优先级 and 开始大改前先读什么.

HWYD/ai-mind · 3,170 tokens

finding-unknowns-skills CLAUDE.md

Claude Code instructions for Neeeophytee/finding-unknowns-skills, covering repo notes, what ships, and the gate that decides, version lives in three manifests — move them together, files that must be edited together and shipped guidance is not this file.

Neeeophytee/finding-unknowns-skills · 1,447 tokens

vvvv-skills CLAUDE.md

Claude Code instructions for tebjan/vvvv-skills, covering vvvv gamma, when to patch vs code, core concepts, live environment and important conventions.

tebjan/vvvv-skills · 987 tokens