orchestrator: Skill for Claude Code

.claude/skills/grpc-regression/SKILL.md

grpc-regression is a skill for Claude Code from c9r-io/orchestrator. It costs 41 tokens per session (337 once invoked), scanned A, original, MIT.

A workflow for checking gRPC services through their real communication channel. gRPC is a way for programs to call functions on another program, often using a defined service interface and binary messages.

In plain words
What is it for?
Use it to run regression checks through the repository's daemon and command-line client, or with Docker-network helpers when the project really uses Docker Compose. It also helps verify RPC behavior against the service definition.
Why use it?
It avoids testing only internal code paths and checks whether requests, authentication, certificates, success cases, and expected errors work across the actual connection.

Skill for Claude Code

Written for Claude Code: installed under .claude/. Also seen: reads .claude/ paths.

This is c9r-io/orchestrator's own configuration. It tells Claude Code how to work on orchestrator itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything orchestrator configures →

Reuse

Borrowing it

Nothing to install: this file belongs to c9r-io/orchestrator. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/c9r-io/orchestrator/main/.claude/skills/grpc-regression/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/c9r-io/orchestrator

Made for: Claude Code.

Wrote 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.

agentmods badge for grpc-regression

README.md
[![agentmods](https://agentmods.dev/badge/skills/c9r-io/orchestrator/grpc-regression/github.svg)](https://agentmods.dev/skills/c9r-io/orchestrator/grpc-regression)
Your own site
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/grpc-regression"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/grpc-regression/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.

agentmods 80×15 button for grpc-regression

Your own site · 80×15
<a href="https://agentmods.dev/skills/c9r-io/orchestrator/grpc-regression"><img src="https://agentmods.dev/badge/skills/c9r-io/orchestrator/grpc-regression.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 41 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 337 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00041 $0.00337
Opus 5 $0.00020 $0.00169
Sonnet 5 $0.00008 $0.00067
Haiku 4.5 $0.00004 $0.00034

Measured 9d ago against content hash 68091b7bda73, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

grpc-regression 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 9d 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.

.claude/skills/grpc-regression/SKILL.md · 34 lines

What it actually says

gRPC Regression

Choose the transport from the repository, not from the skill name.

Agent Orchestrator Repository

The daemon uses ~/.orchestratord/orchestrator.sock by default, overridable by ORCHESTRATORD_DATA_DIR or ORCHESTRATOR_SOCKET. Exercise RPC behavior through the orchestrator CLI unless the daemon was explicitly bound to TCP. Start with:

orchestrator daemon status
orchestrator debug --component daemon
orchestrator check

Use crates/proto/orchestrator.proto as the canonical service definition. For a specific RPC, prefer the matching CLI command and assert both success and its expected error category.

Docker Network Branch

The shared helpers .claude/skills/tools/grpc-smoke.sh and .claude/skills/tools/grpcurl-docker.sh are for a target that actually has a Compose network. Confirm its compose file and network before use; docker/docker-compose.yml is a generated-project convention, not a file in this repository.

Recommended checks when that branch applies:

  1. Missing credentials fail with the expected authentication status.
  2. Valid credentials cross the transport boundary.
  3. Wrong client certificates fail the TLS handshake.
  4. Reflection-disabled services are called with the target's mounted canonical proto.

Never start containers or pull a grpcurl image merely to test the local UDS daemon.

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. 9d ago First seen · 34 lines · 41 tokens per session scan A 68091b7bda73

Subscribe to this mod's changes

grpc-regression is a skill published in the GitHub repository c9r-io/orchestrator (21 stars, last pushed 7d ago), licensed MIT. It adds 41 tokens to every session and 337 once invoked, about $0.0002 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.