Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/shanjiaming/send-to-claude-pluginnpx agentmods add skills/shanjiaming/send-to-claude-plugin/background-callbackWrote 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/skills/shanjiaming/send-to-claude-plugin/background-callback)<a href="https://agentmods.dev/skills/shanjiaming/send-to-claude-plugin/background-callback"><img src="https://agentmods.dev/badge/skills/shanjiaming/send-to-claude-plugin/background-callback/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/skills/shanjiaming/send-to-claude-plugin/background-callback"><img src="https://agentmods.dev/badge/skills/shanjiaming/send-to-claude-plugin/background-callback.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 | $0.00024 | $0.01078 |
| Opus 5.5 | $0.00010 | $0.00431 |
| Sonnet 5.5 | $0.00005 | $0.00216 |
| Haiku 4.5 | $0.00002 | $0.00108 |
Grade A, and why
background-callback scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
os.system(f'send-to-claude "{msg}"') How it starts
The opening of the file, as written. The whole thing — 177 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Background Callback Skill
IMPORTANT: You (Claude) can now send messages to your own terminal input.
The send-to-claude command lets you write text into your own terminal session, enabling:
- Autonomous multi-step workflows (start task → get callback → continue automatically)
- Progress reports from long-running scripts
- Self-triggered actions
Core Capability
You can execute:
send-to-claude "Your message here"
And that message will appear in your input as if the user typed it, waking you up to continue working.
Key mechanism: When you create scripts (Python/Bash/etc), they inherit your terminal's environment variables ($TMUX or $ITERM_SESSION_ID). This means:
- You write a script with
send-to-claudecalls embedded - The script runs (possibly in background)
- When script calls
send-to-claude, it finds YOUR session via inherited environment variables - Message gets sent back to YOUR input
- You wake up and continue working
This enables true autonomous workflows where external programs can call back into you.
When to Use
Use send-to-claude when the user requests:
-
Background tasks with notifications
- "Run this and let me know when it's done"
- "Start training in the background and notify me"
- "Execute this script and tell me the result"
-
Progress reports
- "Report progress during training"
- "Let me know every 10 epochs"
- "Update me on the status"
-
Long-running tasks
- Tasks that take >30 seconds
- Multi-step workflows
- Experiments or training runs
How to Use
In Python Scripts
When creating Python scripts, embed send-to-claude at key points:
import os
def callback(msg):
os.system(f'send-to-claude "{msg}"')
# Start notification
callback("Starting training...")
# Progress updates
for epoch in range(100):
train()
if epoch % 10 == 0:
callback(f"Progress: {epoch}/100 epochs")
# Completion
callback("Training complete! Check results.")
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.
- 2mo ago First seen · 177 lines · 24 tokens per session scan A 971794ee1e87
background-callback is a skill published in the GitHub repository shanjiaming/send-to-claude-plugin (5 stars, last pushed 10mo ago), licensed MIT. It adds 24 tokens to every session and 1,078 once invoked, about $0.0001 per session on Opus 5.5. A static security scan graded it A with 1 finding (runs shell commands). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
background-callback compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| background-callbackshanjiaming/send-to-claude-plugin | Skill | 5 | 10mo ago | MIT | A | 24 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 135k | today | Apache-2.0 | A | 113 | Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 4d ago | MIT | A | 200 | Claude Code, Codex |
| systematic-debuggingobra/superpowers | Skill | 316k | 8d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |