Borrowing it
Nothing to install: this file belongs to connerohnesorge/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/connerohnesorge/claude-agent-sdk-go/main/.claude/agents/stuck.mdgit clone --depth 1 https://github.com/connerohnesorge/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/connerohnesorge/claude-agent-sdk-go/stuck)<a href="https://agentmods.dev/agents/connerohnesorge/claude-agent-sdk-go/stuck"><img src="https://agentmods.dev/badge/agents/connerohnesorge/claude-agent-sdk-go/stuck/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/connerohnesorge/claude-agent-sdk-go/stuck"><img src="https://agentmods.dev/badge/agents/connerohnesorge/claude-agent-sdk-go/stuck.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 | $0.00053 | $0.01125 |
| Opus 5.5 | $0.00021 | $0.00450 |
| Sonnet 5.5 | $0.00011 | $0.00225 |
| Haiku 4.5 | $0.00005 | $0.00112 |
Grade A, and why
stuck 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.
The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
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 · 146 lines · 53 tokens per session scan A 1c6a9847b1cb
stuck is an agent published in the GitHub repository connerohnesorge/claude-agent-sdk-go (24 stars, last pushed 4mo ago), with no licence file. It adds 53 tokens to every session and 1,125 once invoked, about $0.0002 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
planner
Creates lean implementation plans. Breaks work into 2-5 minute tasks grouped into file-disjoint lanes, each with a decision, exact file paths, test assertions, and a verification command. Use when requirements are clear and need systematic task breakdown.
task-reviewer
Reviews one plan lane's diff once and emits two verdicts: Spec compliance and Quality. Use proactively after a lane finishes in --reviewed mode. Reads the actual diff — does NOT trust builder reports. Replaces the former spec-reviewer + quality-reviewer pair (one spawn, one diff-load).
verifier
Tries to refute one finding or review comment about the current code, and returns confirmed, refuted or uncertain with evidence. Read-only. Dispatched once per claim (a review finding or a PR comment).
builder
Implements a plan lane (its tasks in order) following TDD. Use proactively when a plan lane needs implementation. Builds methodically: records rulings → implements with tests → self-reviews → commits by pathspec. Always externalizes decisions to files.
code-reviewer
Senior holistic reviewer for pre-merge assessment. Reviews entire git diff against the original plan for architecture alignment, design quality, and production readiness. Run ONCE after ALL tasks complete, not per-task. Reports merge readiness with reasoning.
researcher
Deep codebase exploration and context gathering. Use proactively when understanding existing code, finding patterns, investigating architecture, or gathering context before planning. Fast, read-only, runs in background by default.