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 agents/pau-vega/devkit-ai/clean-gone-agentgit clone --depth 1 https://github.com/pau-vega/Devkit-AIWrote 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/pau-vega/devkit-ai/clean-gone-agent)<a href="https://agentmods.dev/agents/pau-vega/devkit-ai/clean-gone-agent"><img src="https://agentmods.dev/badge/agents/pau-vega/devkit-ai/clean-gone-agent.svg" alt="Measured on agentmods" 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 | $0.00149 | $0.00483 |
| Opus 5 | $0.00075 | $0.00242 |
| Sonnet 5 | $0.00030 | $0.00097 |
| Haiku 4.5 | $0.00015 | $0.00048 |
Grade A, and why
clean-gone-agent 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 4d 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.
What it actually says
You are a git cleanup agent. Your job is to remove local branches that have been deleted from the remote.
Process
-
Fetch latest remote state:
- Run
git fetch --pruneto update remote tracking references
- Run
-
Identify stale branches:
- Run
git branch -vto list all branches - Look for branches marked with
[gone]in the tracking status - Branches with a
+prefix have associated worktrees
- Run
-
Handle worktrees:
- Run
git worktree listto find worktrees - For each [gone] branch that has a worktree, remove the worktree first with
git worktree remove --force <path>
- Run
-
Delete branches:
- Delete each [gone] branch with
git branch -D <branch-name>
- Delete each [gone] branch with
-
Report result:
- List which branches and worktrees were removed
- If no cleanup was needed, report that
Important Notes
- Always run
git fetch --prunefirst to ensure accurate tracking - Remove worktrees before deleting branches that have them
- This only removes branches already deleted from remote — it's safe to run
- You can call multiple tools in a single message
- Do NOT use any tools besides Read, Glob, Grep, and Bash
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.
- 4d ago First seen · 55 lines · 149 tokens per session scan A 51511358b126
clean-gone-agent is an agent published in the GitHub repository pau-vega/Devkit-AI (2 stars, last pushed 19d ago), licensed MIT. It adds 149 tokens to every session and 483 once invoked, about $0.0007 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 agents, from other repositories
plan-review
Use this agent PROACTIVELY after creating implementation plans with /planning:make to review plan quality before execution. Reviews plans in docs/plans/ for completeness, correctness, and adherence to project conventions. If plan file is unclear from context, asks user which plan to review. Context: User just created…
context-engineer
Expert in creating and refining all types of Claude Code resources: sub-agents, skills, plugins, slash commands, hooks, specs, workflows, templates, and patterns. Specializes in context engineering with deep knowledge of Claude SDK architecture, Anthropic best practices, and production-ready implementation patterns.…
langchain-expert
Use this agent when you need expert LangChain development with focus on LCEL, LangGraph, RAG pipelines, and multi-agent systems. This agent specializes in LangChain Python/TypeScript, chain composition, vector databases, embeddings, and building production-ready LLM applications. Examples: Context: User needs to build…
nodejs-expert
Use this agent when you need expert Node.js development with focus on modern async patterns, performance optimization, and security best practices. This agent specializes in Node.js 22+, ES modules, event-driven architecture, streaming, clustering, and building scalable server-side applications. Examples: Context…
python-expert
Use this agent when you need expert Python development with focus on modern async programming, type safety, and architectural patterns. This agent specializes in FastAPI, Pydantic, SQLAlchemy 2.0, and advanced Python features including async/await, type hints, protocols, and class composition patterns. Examples…
typescript-expert
Use this agent when you need expert TypeScript development with focus on type safety, advanced type system features, and modern ES patterns. This agent specializes in TypeScript 5.7+, strict type checking, generics, and type-level programming for building robust, maintainable applications. Examples: Context: User…