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/cel-expr/skills/claude-mdgit clone --depth 1 https://github.com/cel-expr/skillsWhat 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 | $0.00668 | $0.00668 |
| Opus 5 | $0.00334 | $0.00334 |
| Sonnet 5 | $0.00134 | $0.00134 |
| Haiku 4.5 | $0.00067 | $0.00067 |
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.
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 binaryFileDescriptorSetfile containing protobuf definitions referenced as types within an environment.
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.
- yesterday First seen · 73 lines · 668 tokens per session scan A 47fabe4ba717
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.
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).
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.
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).
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.
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.
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.