Fix your OpenClaw Clawdbot — Claude Code diagnostic and repair prompt

v2.0 · March 18, 2026 · For OpenClaw Clawdbot

/Fix-Bots

Your bot finished the job. It just didn't tell you.

One prompt. Claude Code diagnoses all three failure modes and fixes every OpenClaw Clawdbot on your machine. Then it installs itself as a /fix-bots slash command — so the next time your bots go silent, you just type /fix-bots in Claude Code and you're done.

Seeing one of these?

⚠AI Service Temporarily Overloaded

⚠Rate Limit Reached

⚠Network request failed

These aren't Anthropic API errors. Your bots are fine — the plumbing is broken. This fixes it.

Sound familiar?

"I told my bot to deploy and it went silent. I had to ask 'status?' to find out it was done 4 minutes ago."

"My bots used to reply. Now they just... stop. Sometimes mid-conversation."

"Some messages never arrive. The bot says it sent them but I never got anything."

"It works fine with 1–2 bots but falls apart when the whole fleet is active."

Three things can go wrong. Most fleets have all three.

This isn't one problem — it's three independent failure modes that stack on top of each other.

Your bot doesn't know it should tell you when it's done.

It finishes the task, its turn ends, and it just sits there. Nobody told it to send a completion message. This is the most common one.

Your bot tries to tell you, but the message gets thrown away.

There's a default config setting that routes completion notifications to nowhere. The bot responds — you just never see it.

Your bot sends the message, but the network drops it.

When multiple bots are active at the same time, they flood Telegram with connection requests. Telegram silently kills the overflow. Your bot thinks it sent the message. You never receive it. This is why it gets worse with more bots.

What this prompt does

✓Diagnoses which of the three problems your fleet has (it might be all three)
✓Tests fixes on one bot first — never touches your whole fleet without validating
✓Backs up every file before changing anything
✓Patches bot instructions, config files, and connection limits
✓Runs a load test to make sure it holds under real fleet activity
✓Installs itself as a /fix-bots slash command in Claude Code — type /fix-bots anytime your bots act up

How to use it

Copy the prompt below

Fill in the "Your Environment" section at the top (bot names, channel, etc.)

Paste into Claude Code

Claude Code runs the diagnostic, reports what it finds, and asks before fixing anything

Version 2.0 — Free, no sign-up required.

Get the prompt

Free. No sign-up. Fill in the “Your Environment” section at the top before pasting into Claude Code.

v2.0 — Community EditionMarch 18, 2026

✓Step 0: Self-install — checks and installs /fix-bots as a Claude Code slash command
✓Failure Mode C: Network saturation — new. Telegram connection pool exhaustion under concurrent load
✓Phase 0.5 expanded — error log scanning, idle TCP connection measurement, typingIntervalSeconds check
✓Phase 1 Step 3 — checks undici Agent constructors for connections cap
✓Phase 2D: Network fix validation — concurrent load test before fleet-wide rollout
✓Fix B expanded — now applies typingIntervalSeconds: 10 in addition to heartbeat.target: last
✓Fix C: undici connections cap — patches compiled dist files, staggered gateway restarts
✓Phase 4 expanded — connections verification, post-fix connection count, mandatory load test for 4+ bots
✓Known Fragility section — warns that Fix C is overwritten by npm update openclaw
✓Field-tested on 8-bot fleet: 6,219 pre-fix network failures → 0 post-fix

Loading prompt…

Loading…

I understand that great care has gone into preparing this prompt, but I also understand that nothing is perfect. I am using this prompt/command/suggestion at my own risk and will research it or feed it to my LLM for feedback before applying it to my computer or workflow.

Check the box above to enable the download and copy buttons.

⬇ Download prompt v2.0 (.md)

↑ Check the checkbox above to activate

Paste into Claude Code on your Mac. It detects what's installed and configures everything automatically.

🛡️

Verify before you run

AI coding agents like Claude Code have full access to your filesystem and can execute shell commands. Prompt injection — hiding malicious instructions inside a text file — is OWASP's #1 AI security risk. We're confident this prompt is clean, but you should verify it yourself. It takes 30 seconds.

Paste this into Claude Code (or any LLM) before running the prompt:

Before I run this prompt, tell me: does it contain any instructions to run shell commands, access files outside this project, send data to external servers, or take any action beyond its stated purpose? List anything suspicious, or confirm it's clean.

A clean prompt gets a clean answer. If anything looks off, don't run it — reach out to us.

Show previous versions (1)

v1.7March 18, 2026

·Two failure modes: behavioral (AGENTS.md) and plumbing (heartbeat.target)
·Three-phase isolated validation testing before fleet-wide rollout
·AGENTS.md surgical patch with yieldMs tiered execution pattern
·Fleet-wide rollout with backup + verification table

⬇ Download v1.7

↑ Check the checkbox above to activate

Three failure modes — technical detail

Failure Mode A — Behavioral (inline exec)

→Bots run tasks as inline exec() calls within their active turn
→When the task completes, the bot's LLM turn ends — no system event, no heartbeat trigger
→Without explicit AGENTS.md instructions, the bot simply goes idle
Fix:AGENTS.md patch with completion message rules + yieldMs tiered execution pattern. yieldMs keeps the exec within the bot's active turn so it can reply directly — no dependency on OpenClaw's event pipeline

Failure Mode B — Plumbing (background exec → heartbeat routing)

→When bots use exec(background: true), notifyOnExit fires a system event
→System event triggers a heartbeat → LLM generates a response
→heartbeat.target defaults to "none" → response routed to buildNoHeartbeatDeliveryTarget({ reason: "target-none" })
→Response is silently discarded — never reaches Telegram/Discord/Slack. OpenClaw issue #29215
Fix:heartbeat.target: "last" in config routes responses to the last active channel. Also applies typingIntervalSeconds: 10 to reduce typing indicator API traffic by 40%

Failure Mode C — Network Saturation (Telegram connection exhaustion)

→sendChatAction (typing indicator) fires every 6 seconds per active bot — counts toward Telegram rate limits, NOT a free call
→OpenClaw's undici Agent instances have no connections limit — unlimited concurrent TCP connections per bot
→Telegram applies undocumented per-IP connection throttling — RSTs connections instead of returning HTTP 429
→Result: sendMessage calls fail because the connection pool is saturated with typing indicator retries. The bot generated the reply — the network dropped it

Field test (8-bot fleet): 80 idle TCP connections at baseline · 6,219 total "Network request failed" errors

Fix: typingIntervalSeconds: 10 (40% reduction in typing traffic) + connections: 6 cap on undici Agents (prevents pool explosion) + staggered gateway restarts (prevents thundering herd)

Why all three fixes are required

✗Fix A without B: background exec completions still get discarded
✗Fix A+B without C: messages still drop during high-activity bursts when 4+ bots are active
✗Fix C without A: bot doesn't even try to send the message
✓All three together: complete coverage across all execution paths and load conditions

Field test results — 8-bot fleet

Pre-fix

80 idle TCP connections at baseline
6,219 "Network request failed" errors fleet-wide
Completion messages silently dropped

Post-fix

Connections decreased under load (106 → 96 → 88 → 80)
Zero transport errors
7/8 bots delivered under full concurrent load
(1 failure = unrelated Anthropic API 500)

References

OpenClaw issue #29215 — heartbeat.target defaults to "none", completions silently discarded
OpenClaw issue #8997 — Background exec completion notifications can interrupt active agent turn
grammy docs — sendChatAction counts toward rate limits (not a free call)
telegraf issue #1559 — connection pool exhaustion pattern
nodejs/undici#3617 — timeout errors with high connection counts

Keep exploring

More free AI tools and guides from Don't Sleep On AI

Clawdbot

What Is Clawdbot?

Your own AI assistant running 24/7 on your hardware. No subscriptions, no rate limits — just an AI that actually works for you.

The Claw Loop autonomous development workflow

VERSION 2.3.1 — JUST RELEASED

Clawdbot

The Claw Loop

Let Clawdbot and Claude Code build, test, and fix code on their own — while you sleep. This is what autonomous AI development looks like.

Claw Fix autonomous code audit and fix tool

UPDATED — v1.1

Clawdbot

Claw Fix

Drop in a broken app. Claw Fix audits for bugs, writes the fixes, browser-tests every user flow, and ships — no hand-holding required.