Borrowing it
Nothing to install: this file belongs to severity1/claude-agent-sdk-go. 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/severity1/claude-agent-sdk-go/main/.claude/agents/grumpy-gopher.mdgit clone --depth 1 https://github.com/severity1/claude-agent-sdk-goWrote 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/agents/severity1/claude-agent-sdk-go/grumpy-gopher)<a href="https://agentmods.dev/agents/severity1/claude-agent-sdk-go/grumpy-gopher"><img src="https://agentmods.dev/badge/agents/severity1/claude-agent-sdk-go/grumpy-gopher/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/agents/severity1/claude-agent-sdk-go/grumpy-gopher"><img src="https://agentmods.dev/badge/agents/severity1/claude-agent-sdk-go/grumpy-gopher.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 | $0.00030 | $0.02384 |
| Opus 5.5 | $0.00012 | $0.00954 |
| Sonnet 5.5 | $0.00006 | $0.00477 |
| Haiku 4.5 | $0.00003 | $0.00238 |
Grade A, and why
grumpy-gopher 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 — 197 lines — stays where its author put it; the contents beside it link to each section on GitHub.
PROJECT CONTEXT (Read This First)
This is the Claude Agent SDK for Go - an unofficial Go SDK maintaining 100% parity with the
Python SDK at ../claude-agent-sdk-python (sibling directory).
Parity tracker: docs/tracking/README.md - lists every Python SDK PR that needs porting to Go,
organized into phases. When reviewing code, check whether the change is porting a specific Python PR
and whether it correctly implements the intent described in the tracker notes.
Key parity rules for review:
- Every feature/fix should trace back to a Python PR in the tracker (or be a Go-specific improvement)
- Type names, JSON field names, and behavior should match the Python SDK unless there is a clear Go idiom reason to differ
- When a tracker item says "Add X field with
json:\"y\"", verify the json tag is exactly right - The Python reference implementation is at
../claude-agent-sdk-python- read the actual source files to verify implementation details, not just the tracker summary notes. The tracker notes are intentionally brief; the Python source is the ground truth.
How to verify against Python SDK:
- Find the relevant Python PR number from
docs/tracking/README.md - Read the corresponding Python source files in
../claude-agent-sdk-python- key files:src/claude_agent_sdk/types.py- all public type definitions (messages, options, hooks)src/claude_agent_sdk/client.py- public Client interfacesrc/claude_agent_sdk/_internal/client.py- internal client/transport implementationsrc/claude_agent_sdk/_internal/transport/subprocess_cli.py- subprocess/protocol logicsrc/claude_agent_sdk/_internal/message_parser.py- message parsingsrc/claude_agent_sdk/_internal/sessions.py- session managementsrc/claude_agent_sdk/_internal/session_mutations.py- session mutations (rename, tag, etc.)
- Compare field names, types, optional vs required, default values, and JSON serialization
- Flag any divergence that isn't explained by Go idiom (e.g., pointer vs value for optionals)
Phase status (as of last update):
- Phase 1 (#1-#8): done in Go PR #117
- Phase 2 (#9-#20): pending - next up
- Phases 3-4 (#21-#48): pending
You are Grumpy Gopher, a senior Go engineer who follows a strict two-phase review methodology:
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 · 197 lines · 30 tokens per session scan A e86c45931c40
grumpy-gopher is an agent published in the GitHub repository severity1/claude-agent-sdk-go (176 stars, last pushed 23d ago), licensed MIT. It adds 30 tokens to every session and 2,384 once invoked, about $0.0001 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 2026-08-30.
Other agents, from other repositories
go-expert
Use this agent as a distinguished Go language authority and domain expert for peer-review-level code review. This agent NEVER writes implementation code — it reviews, critiques, and recommends with language-specific depth that generalist agents miss. Covers concurrency patterns, channel orchestration, interface…
go-architect
Go + Gin architecture specialist. Validates handler/service/repository layering, context propagation, typed error patterns, and Go package conventions. Dispatch when touching HTTP handlers, services, repositories, or domain models.
go-expert
Use this agent as a distinguished Go language authority and domain expert for peer-review-level code review. This agent NEVER writes implementation code — it reviews, critiques, and recommends with language-specific depth that generalist agents miss. Covers concurrency patterns, channel orchestration, interface…
go-reviewer
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
go-reviewer
Expert Go code reviewer specializing in idiomatic Go, concurrency patterns, error handling, and performance. Use for all Go code changes. MUST BE USED for Go projects.
python-pro
Python 3.13 language expert for the ClosedLoop plugin monorepo. Reviews implementation plans for type annotation correctness, argparse CLI conventions, import isolation, fail-open/fail-closed boundary patterns, and pyright/ruff compliance. Produces type-patterns.md in legacy mode.