Automated summary
Walks through installing and configuring the Manifest observability plugin for a Claude Code agent, from stopping the gateway to verifying it in the logs.
Strengths
- Numbered, ordered steps with the exact CLI commands to run
- Enforces API key format validation (mnfst_ prefix) and never echoing the key in plain text
- Troubleshooting table covering common errors, including the conflict with the built-in diagnostics-otel plugin
- Supports self-hosted endpoints in addition to the default one
Limitations
- Tied to the Manifest platform, so it is useless for any other observability tool
- Assumes the claude CLI, the gateway command, and the ~/.claude/logs/gateway.log path exist in the environment
- Does not cover dashboard design or alerting rules
Use it when a user wants to connect their agent to Manifest for monitoring, set an API key or custom endpoint, or debug a failing plugin connection.
Skip it when the user needs general observability design, custom dashboards or alerting rules, or is not using the Manifest platform.
Security analysis
CautionThe skill is not overtly malicious and its commands are consistent with plugin setup, but it handles an API key in a way that may expose it through command history/process arguments and asks for the secret in chat. It also performs CLI, plugin-installation, gateway, and log-reading operations without declared allowed-tools, so it warrants caution rather than a safe rating.
- •No allowed-tools are declared, yet the skill instructs the agent to run shell commands that modify CLI configuration and gateway state.
- •Step 4 passes the API key directly as a command-line argument via `claude config set plugins.entries.manifest.config.apiKey "USER_API_KEY"`, which can expose the secret in shell history or process listings.
- •The skill asks the user to paste a manifest API key into the chat, creating a potential secret-exposure path before configuration.
- •The skill installs a third-party plugin and stops/starts the gateway, which are powerful system/config operations for a legitimate setup purpose.
Examples
Use @manifest to set up observability for my agent.Use @manifest to connect my agent to my self-hosted Manifest instance at https://manifest.internal.company.com/api/v1/otlpMy Manifest plugin isn't sending telemetry — can you check the gateway logs and get it working again?name: manifest description: "Install and configure the Manifest observability plugin for your agents. Use when setting up telemetry, configuring API keys, or troubleshooting the plugin." risk: unknown source: community date_added: "2026-02-27"
Manifest Setup
Follow these steps in order. Do not skip ahead.
Use this skill when
- User wants to set up observability or telemetry for their agent
- User wants to connect their agent to Manifest for monitoring
- User needs to configure a Manifest API key or custom endpoint
- User is troubleshooting Manifest plugin connection issues
- User wants to verify the Manifest plugin is running
Do not use this skill when
- User needs general observability design (use
observability-engineerinstead) - User wants to build custom dashboards or alerting rules
- User is not using the Manifest platform
Instructions
Step 1 — Stop the gateway
Stop the gateway first to avoid hot-reload issues during configuration.
claude gateway stop
Step 2 — Install the plugin
claude plugins install manifest
If it fails, check that the CLI is installed and available in the PATH.
Step 3 — Get an API key
Ask the user:
To connect your agent, you need a Manifest API key. Here's how to get one:
- Go to https://app.manifest.build and create an account (or sign in)
- Once logged 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.
Step 4 — Configure the plugin
claude config set plugins.entries.manifest.config.apiKey "USER_API_KEY"
Replace USER_API_KEY with the actual key the user provided.
Ask the user if they have a custom endpoint. If not, the default (https://app.manifest.build/api/v1/otlp) is used automatically. If they do:
claude config set plugins.entries.manifest.config.endpoint "USER_ENDPOINT"
Step 5 — Start the gateway
claude gateway install
Step 6 — Verify
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.
Safety
- Never log or echo the API key in plain text after configuration
- Verify the key format (
mnfst_prefix) before writing to config
Troubleshooting
| Error | Fix |
|-------|-----|
| Missing apiKey | Re-run step 4 |
| Invalid apiKey format | The key must start with mnfst_ |
| Connection refused | The endpoint is unreachable. Check the URL or ask if they self-host |
| Duplicate OTel registration | Disable the conflicting built-in plugin: claude plugins disable diagnostics-otel |
Examples
Example 1: Basic setup
Use @manifest to set up observability for my agent.
Example 2: Custom endpoint
Use @manifest to connect my agent to my self-hosted Manifest instance at https://manifest.internal.company.com/api/v1/otlp
Best Practices
- Always stop the gateway before making configuration changes
- The default endpoint works for most users — only change it if self-hosting
- API keys always start with
mnfst_— any other format is invalid - Check gateway logs first when debugging any plugin issue
From the file to a first result
The download contains exactly the content displayed on this page. This copy may differ from the latest version in the source repository.
View the source and supporting filesThis download contains SKILL.md only. Any scripts, references, templates and dependencies are not included. Get the required files from the source, preserving their directory structure, before continuing.
1. Download the file
Download SKILL.mdFrom the root of a test project, save the file as .skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md, or use the command below. This folder is for inspecting the skill before installation.
Command for macOS/Linux or WSL: requires a POSIX shell and curl. On Windows without WSL, use the download button and create the folder manually.
mkdir -p '.skill-downloads/manifest-plugin-setup-mma3jshy' && curl --fail --show-error --location 'https://skills-guides.com/api/skills/manifest-plugin-setup-mma3jshy/download' --output '.skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md.part' && mv '.skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md.part' '.skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md'2. Check prerequisites
Read SKILL.md before using it. If it references scripts or external services, inspect them and prepare the required access in your test environment.
No recognized prerequisites section in this file. This does not mean it is self-contained: libraries, tools and access requirements may be mentioned elsewhere in the content or source repository.
The platforms on this page are catalog indications. The paths below follow tool documentation; they do not prove this skill has been run in those tools. No minimum tool version is confirmed for this listing.
3. Load the skill
After inspection, copy the complete folder into your project using one of the commands below, then open a new tool session. The command stops if a folder with the same name already exists: compare the files before replacing it.
Claude Code
test -f '.skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md' && test -s '.skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md' && mkdir -p '.claude/skills' && test ! -e '.claude/skills/manifest' && cp -R '.skill-downloads/manifest-plugin-setup-mma3jshy' '.claude/skills/manifest'OpenSkills
OpenSkills must already be installed. The local install/read procedure is checked with OpenSkills 1.5.0, which requires Node.js ≥ 20.6.0. Catalog slugs are not resolved automatically.
Official OpenSkills installationopenskills install './.skill-downloads/manifest-plugin-setup-mma3jshy'openskills read 'manifest-plugin-setup-mma3jshy'Reading should display the installed file content and its base directory. It does not run the skill or install its dependencies.
For an agent that reads AGENTS.md, then sync the index. This command changes AGENTS.md: review the diff before using it.
openskills syncManual method or another tool: attach SKILL.md to a conversation, or open it in an agent that can read files. Include any required supporting resources. No universal folder is recognized by every tool.
4. Try a first task
Use a short, synthetic input: an API endpoint, a small document or an interface brief. In a new conversation, attach the file or give the agent its path, then adapt this request:
Read .skill-downloads/manifest-plugin-setup-mma3jshy/SKILL.md and apply its instructions to this example: [describe a test input]. Identify any missing files, dependencies or access. Produce the result requested by the skill without inventing data or running unreviewed scripts.Expected result: output matching the skill instructions, or a precise list of missing prerequisites. A read confirmation alone does not validate a first use. If an external resource is unavailable, that path remains untested.
Configure a Chat Channel with SecretRefs
DevOps
Set up chat channels using non-interactive commands, with secrets only as SecretRefs. Covers gather, mutate, repair, and prove steps for reliable delivery.
Investigate ClickHouse CI Failures
DevOps
Investigate a ClickHouse CI failure end-to-end from a PR or S3 report URL. Fetches failed tests, classifies flaky vs real regression, and checks for existing issues/fixes.
Ansible PR Review
DevOps
Reviews an Ansible PR following the project's standardized process, including changelog checks, test coverage validation, and feedback tracking.