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 instructions/zebbern/icron/claude-mdgit clone --depth 1 https://github.com/zebbern/icronWhat 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 | $0.00742 | $0.00742 |
| Opus 5 | $0.00371 | $0.00371 |
| Sonnet 5 | $0.00148 | $0.00148 |
| Haiku 4.5 | $0.00074 | $0.00074 |
Grade A, and why
icron CLAUDE.md 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 2d 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 — 106 lines — stays where its author put it; the contents beside it link to each section on GitHub.
icron
A lightweight personal AI assistant framework with multi-channel support.
Architecture
User -> Channel -> MessageBus -> AgentLoop -> LLM Provider
| |
v v
SessionStore ToolRegistry (18 tools + MCP)
Channels: Discord, Telegram, WhatsApp, Slack, Feishu
Providers: Anthropic, OpenAI, OpenRouter, Together, Groq, Gemini, Zhipu, vLLM
Config: ~/.icron/config.json
Key Directories
icron/
├── agent/ # Core agent loop, tools, context
├── channels/ # Discord, Telegram, WhatsApp, Slack, Feishu
├── bus/ # Async message bus
├── config/ # Pydantic config schema
├── cron/ # Scheduled jobs service
├── mcp/ # Model Context Protocol client
├── session/ # JSONL conversation storage
├── cli/ # Typer CLI commands
ui/ # Svelte web settings UI
bridge/ # Node.js WhatsApp bridge
Built-in Tools
| Category | Tools |
|---|---|
| Files | read_file, write_file, edit_file, list_dir, rename_file, move_file, copy_file, create_dir |
| Search | glob, grep |
| Web | web_search (Brave), web_fetch |
| Shell | exec |
| Memory | remember, recall, note_today |
| Scheduling | set_reminder, list_reminders, cancel_reminder, cron |
| Communication | message, spawn |
Commands
icron onboard # Initialize config + workspace
icron gateway # Start full server (web UI at :3883)
icron agent -m "..." # Direct chat + REPL mode
icron cron list # Manage scheduled jobs
icron status # Show configuration
Code Patterns
Tool Implementation
class MyTool(Tool):
def __init__(self, workspace: Path | None = None):
self.workspace = workspace
@property
def name(self) -> str:
return "my_tool"
@property
def description(self) -> str:
return "Does something useful"
@property
def parameters(self) -> dict[str, Any]:
return {"type": "object", "properties": {...}}
async def execute(self, **kwargs: Any) -> str:
try:
return "result"
except Exception as e:
return f"Error: {e}" # Return errors, don't raise
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.
- 2d ago First seen · 106 lines · 742 tokens per session scan A 65ad8c6b8cef
icron CLAUDE.md is an instructions file published in the GitHub repository zebbern/icron (5 stars, last pushed 6mo ago), licensed MIT. It adds 742 tokens to every session, about $0.0037 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 instructions, from other repositories
open-bridge AGENTS.md
Instructions for bks-lab/open-bridge, covering the bridge — agent instructions, required reading, session start detection (automatic), theme and agents.
awesome-harness-engineering CLAUDE.md
Claude Code instructions for ai-boost/awesome-harness-engineering, a project described as: Awesome list for AI agent harness engineering: tools, patterns, evals, memory, MCP, permissions, observability, and orchestration.
open-bridge CLAUDE.md
Instructions for bks-lab/open-bridge, a project described as: Your AI coding agent starts every session knowing your repos, your clients, and how you work — a plain git repo of markdown + YAML it reads at session start, independent of model or frontend. Context compounds instead of restarting. MIT.
swarm-357 CLAUDE.md
Instructions for TechTideOhio/swarm-357, covering claude.md, what this repo is, python package (packages/techtide-swarm/), or from pypi and key classes.
COORD-Harness AGENTS.md
AGENTS.md instructions for 0marm0/COORD-Harness, covering coordharness agent entrypoint, start and finish and context hierarchy.
agent-memory-kit CLAUDE.md
Claude Code instructions for awrshift/agent-memory-kit, covering working on memory kit, rules that are easy to get wrong, before committing a change to hooks or skills, docs that must stay true in the same commit and language.