agentmods.dev

agetor: Instructions file for Claude Code

CLAUDE.md

agetor CLAUDE.md is an instructions file for Claude Code from alamops/agetor. It costs 14,872 tokens per session, scanned C, original, MIT.

A repository guide for Agetor, a desktop app that runs coding agents from a task board. It explains the app's structure, technologies, and how its Bun process and React interface work together.

In plain words
What is it for?
Use it when developing Agetor, changing its task board, agent process handling, database, HTTP API, or React interface.
Why use it?
It gives a coding agent the project context needed to make changes without confusing Electrobun with Electron or mixing up the app's two processes.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions subagents; names the AskUserQuestion tool.

This is alamops/agetor's own configuration. It tells Claude Code how to work on agetor 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 agetor configures →

not rated 123repo +12 changed 4d ago C scan ✓ AI review 14,872 tokens original MIT
View source ↗ alamops/agetor agetor.dev
Reuse

Borrowing it

Nothing to install: this file belongs to alamops/agetor. 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/alamops/agetor/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/alamops/agetor

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 agetor CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/alamops/agetor/claude-md/github.svg)](https://agentmods.dev/instructions/alamops/agetor/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/alamops/agetor/claude-md"><img src="https://agentmods.dev/badge/instructions/alamops/agetor/claude-md/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 agetor CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/alamops/agetor/claude-md"><img src="https://agentmods.dev/badge/instructions/alamops/agetor/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 14,872 This file is loaded in full into every session.
When invoked 14,872 The same file — it is already loaded in full.
Security scan C 2 findings. A grade says what 26 rules found in the file — not that it is safe. ✓ AI security review Sonnet 5 · 7 Sept 2026 📄 Read the review
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 $0.14872 $0.14872
Opus 5.5 $0.05949 $0.05949
Sonnet 5.5 $0.02974 $0.02974
Haiku 4.5 $0.01487 $0.01487

Measured 4d ago against content hash c29f1119d49d, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade C, and why

agetor CLAUDE.md scanned grade C with 2 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

4. `DELETE /tasks/:id` kills any active run, then best-effort `git worktree remove --force` + `git branch -D` (with an `rm -rf` fallback under `dataDir/worktrees/`). It never blocks the delete.

Runs shell commandslowCapability

Expected in a hook, worth knowing in a rule or an instructions file.

- **Every spawn goes through `coreSpawn` / `coreSpawnSync`.** A raw `Bun.spawn`, `spawnSync`, `child_process` or `Bun.$` in `src/bun` or `src/shared` fails `core-spawn-allowlist.test.ts`; call sites never call `disclaimA
CLAUDE.md · 329 lines

How it starts

The opening of the file, as written. The whole thing — 329 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

It holds what every change needs: the architecture in brief, the rules that apply everywhere, the commands, the conventions and the known traps. The full contract of each subsystem (routes, invariants, edge cases, test seams) lives in docs/architecture/. Before you change a subsystem, read its doc from the Topic map. The long ones are easier to grep for the symbol you're touching than to read end to end. When a change alters a subsystem's behavior, update its doc in the same change, and add to this file only what every task needs to know.

What this is

Agetor is a local desktop app that orchestrates CLI coding agents (Claude Code, OpenAI Codex, others) from a kanban board. Each task is a prompt + working directory + agent choice; running it spawns the agent as a child process, streams its stdout/stderr to the UI, and moves the card through columns based on exit status.

It is Electrobun (not Electron) — native webviews driven by a Bun main process. Do not reach for Electron APIs, IPC patterns, or Node-only modules.

Stack and architecture

Two processes share this repo and a small shared types directory:

  • Bun main process (src/bun/) owns the Electrobun BrowserWindow, a SQLite store, and an HTTP API the webview talks to. The webview is loaded either from the Vite dev server (http://localhost:5173 when present) or from the bundled views://mainview/index.html.
  • React webview (src/mainview/) renders the kanban board with dnd-kit, talks to the Bun side over fetch + SSE, and uses hand-rolled shadcn/ui primitives styled with Tailwind v3 + CSS variables.
  • Shared (src/shared/types.ts) is the only place both processes import from. Keep it free of runtime imports from either side.

The browser ↔ main connection is intentionally a localhost HTTP API (Bun.serve on AGETOR_API_PORT, default 4317), not Electrobun's RPC. In brief (the full contract is security.md; the rationale and decisions D1–D26 are in docs/plans/master-token-agent-read.md):

Read the full file on GitHub · 329 lines

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. 4d ago Changed · +1 lines · +500 tokens per session c29f1119d49d
  2. 5d ago Changed · +45 lines · -35,050 tokens per session scan F → C 5900d9a09209
  3. 1mo ago Changed · +2 lines · +761 tokens per session 1962e80d1d59
  4. 1mo ago Changed · +2 lines · +2,232 tokens per session 78bf5c57c5de
  5. 1mo ago Changed · +11 lines · +6,655 tokens per session 043e62f68d5d
  6. 1mo ago Changed · +1 lines · +5,121 tokens per session d360ce5bbbe3
  7. 1mo ago Changed · +3,312 tokens per session 1dcc1d71519f
  8. 2mo ago Changed · +1 lines · +317 tokens per session 996aa26d7d01
  9. 2mo ago Changed · +2 lines · +4,835 tokens per session f04abdb0b9fd
  10. 2mo ago First seen · 264 lines · 26,189 tokens per session scan F d7a451432a0c

Subscribe to this mod's changes

agetor CLAUDE.md is an instructions file published in the GitHub repository alamops/agetor (123 stars, last pushed today), licensed MIT. It adds 14,872 tokens to every session, about $0.0595 per session on Opus 5.5. A static security scan graded it C with 2 findings (recursive force delete, runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Claude Codeagent-orchestrationai-agentai-codingai-engineeringai-tools
Related

agetor CLAUDE.md compared with instructions from other repositories

agetor CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
agetor CLAUDE.mdalamops/agetorInstructions file123todayMITC14,872Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA9,719GitHub Copilot
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA5,516GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file143ktodayMITA7,461Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchainInstructions file149ktodayMITA4,680Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA3,093GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscodeInstructions file195ktodayMITA2,022GitHub Copilot