All loopslinkedin
AgentsHard 7 min· claude-haiku-4-5
LinkedIn auto-reply
Drafts polite replies to LinkedIn DMs in your voice.
Read the full Agents build guide →NOT DEPLOYEDNOT DEPLOYED
0196ms
Trigger
cron(0 7 * * *) fired · every day · 07:00
021156ms
Agent
claude-haiku-4-5 · in 1656 tok · out 724 tok
03146ms
Tools
fetch-mcp/anthropic:messages.create → 200 OK · 416ms
0486ms
Verify
schema check · zod v3 passed
05176ms
Output
human review requested · #approvals
0656ms
Notify
audit log written · runbook link attached
SUCCESS
0%
0 runs
P50
0ms
median
P95
0ms
tail
AVG COST
—
per run
LAST OK
never
—
LAST FAIL
never
none
Latency · last 30 runs0 samples
no runs yet
Latest output · what your users see
Agents · Long-running/ Checkpoint · run 148
Subtasks completed
3 / 5 · avg 42s each
Pending human review
1 · refund > $500 threshold
Next tick
resume in 90s from checkpoint c8f21a
// press Test to run once · Watch live to keep streaming · Deploy to make it real
The problem
The outcome
Recruiter DMs are a tax on builders.
Ingredients & skills
Secrets
- ANTHROPIC_API_KEY
Providers
- Anthropic
MCP servers
- fetch-mcp
#agent#automation#claude
How it works
Drafts polite replies to LinkedIn DMs in your voice.
Step 1
1 — Define the loop
Single tool-using loop. Claude decides which MCP tool to call until it has enough context.
Step 2
2 — Bind the locker
The locker contains the Anthropic key plus any provider-specific tokens. Nothing is hardcoded.
Step 3
3 — Schedule or trigger
Either cron, webhook, or on-demand from the Locker UI.
One-line deploy
The button above runs the same command with your saved config. This is the raw CLI form.
bash
npx claudeloops deploy linkedin-auto-reply