Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys or endpoints, troubleshooting plugin connection issues, or verifying the observability pipeline is running.
Set up real-time observability for your AI agents with the Manifest plugin. Monitors costs, tokens, messages, and performance via OTLP telemetry.
Use this skill when:
Follow these steps in order. Do not skip ahead.
Stop the gateway first to avoid hot-reload issues during configuration.
claude gateway stop
claude plugins install manifest
If it fails, check that the CLI is installed and available in the PATH.
Ask the user:
To connect your agent, you need a Manifest API key:
- Go to https://app.manifest.build and create an account (or sign in)
- Click "Connect Agent" to create a new agent
- Copy the API key that starts with
mnfst_- Paste it here
Wait for a key starting with mnfst_. If the key doesn't match, tell the user the format looks incorrect and ask them to try again.
claude config set plugins.entries.manifest.config.apiKey "USER_API_KEY"
Replace USER_API_KEY with the actual key the user provided.
If the user has a custom endpoint (self-hosted):
claude config set plugins.entries.manifest.config.endpoint "USER_ENDPOINT"
The default endpoint (https://app.manifest.build/api/v1/otlp) is used automatically if none is specified.
claude gateway install
Wait 3 seconds for the gateway to fully start, then check the logs:
grep "manifest" ~/.claude/logs/gateway.log | tail -5
Look for:
[manifest] Observability pipeline active
If it appears, tell the user setup is complete. If not, check the error messages and troubleshoot.
| Error | Fix |
|-------|-----|
| Missing apiKey | Re-run Step 4 with the correct key |
| Invalid apiKey format | Key must start with mnfst_ |
| Connection refused | Endpoint is unreachable — check the URL or ask if self-hosting |
| Duplicate OTel registration | Disable the conflicting built-in plugin: claude plugins disable diagnostics-otel |
mnfst_ — any other format is invalidCopy a source-pinned command for your client. You run it yourself.
Destination: .claude/skills/manifest · pinned to the source commit
# Run from your project root
git clone https://github.com/davila7/claude-code-templates.git .skillboard-tmp
git -C .skillboard-tmp checkout 5cc17cf267132cc690dee82239b80a99ec82e4f8
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/cli-tool/components/skills/development/manifest" ".claude/skills/"
rm -rf .skillboard-tmpReview the source before running. This copies files into your project; it is not a one-click install and does not verify runtime safety.
sudo apt update && sudo apt install -y gitnpm install -g @anthropic-ai/claude-code# Run from your project root
git clone https://github.com/davila7/claude-code-templates.git .skillboard-tmp
git -C .skillboard-tmp checkout 5cc17cf267132cc690dee82239b80a99ec82e4f8
mkdir -p ".claude/skills"
cp -r ".skillboard-tmp/cli-tool/components/skills/development/manifest" ".claude/skills/"
rm -rf .skillboard-tmpDestination: .claude/skills/manifest
Scanner static-checks@0.1.0 · commit 5cc17cf26713. Static checks cannot prove runtime safety – review the source and the exact diff before installing. How checks work.
References credentials, tokens or secret files that a skill should not need.
Evidence: [redacted]· fingerprint 61ea4113f56ba6e8