Agent skill

Agent Log Debugging

A skill your agent uses when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs.

AGPL-3.0Auto-check: notesDevelopment

Install Agent Log Debugging

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.claude/skills/agent-log-debugging .claude/skills/agent-log-debugging && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Paste into Claude Code

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .claude/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

Claude Code copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

$skill-installer

$skill-installer install https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging

Type this inside Codex. $skill-installer <name> installs a curated skill from openai/skills. The installer writes to $CODEX_HOME/skills (default ~/.codex/skills). Restart Codex if the skill does not show up.

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a codex

Project install goes to .agents/skills/; add -g for ~/.codex/skills/.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging --agent codex

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .agents/skills && cp -r skills-src/.claude/skills/agent-log-debugging .agents/skills/agent-log-debugging && rm -rf skills-src

Use ~/.agents/skills/ instead of .agents/skills for a personal install.

Codex skills documentation · loads skills from .agents/skills/

Paste into Codex

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .agents/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

Codex copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a cursor

Project install goes to .agents/skills/; add -g for ~/.cursor/skills/.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging --agent cursor

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .cursor/skills && cp -r skills-src/.claude/skills/agent-log-debugging .cursor/skills/agent-log-debugging && rm -rf skills-src

Use ~/.cursor/skills/ instead of .cursor/skills for a personal install.

Cursor skills documentation · loads skills from .cursor/skills/, .agents/skills/, .claude/skills/, .codex/skills/

Paste into Cursor

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .cursor/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

Cursor copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

gemini skills install

$ gemini skills install https://github.com/LanternOps/breeze.git --path .claude/skills/agent-log-debugging

--scope user (default) or --scope workspace; --path is the subfolder of the repo that holds the skill; --consent skips the security confirmation prompt.

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a gemini-cli

Project install goes to .agents/skills/; add -g for ~/.gemini/skills/.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging --agent gemini-cli

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .gemini/skills && cp -r skills-src/.claude/skills/agent-log-debugging .gemini/skills/agent-log-debugging && rm -rf skills-src

Use ~/.gemini/skills/ instead of .gemini/skills for a personal install, then run /skills reload.

Gemini CLI skills documentation · loads skills from .gemini/skills/, .agents/skills/

Paste into Gemini CLI

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .gemini/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

Gemini CLI copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging

Installs for Copilot at project scope by default; add --scope user for a personal install. Preview a skill first with gh skill preview. Needs GitHub CLI 2.90.0 or later (public preview).

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a github-copilot

Project install goes to .agents/skills/; add -g for ~/.copilot/skills/.

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .github/skills && cp -r skills-src/.claude/skills/agent-log-debugging .github/skills/agent-log-debugging && rm -rf skills-src

Use ~/.copilot/skills/ instead of .github/skills for a personal install. Commit .github/skills so cloud agent and code review can use it.

GitHub Copilot skills documentation · loads skills from .github/skills/, .claude/skills/, .agents/skills/

Paste into GitHub Copilot

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .github/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

GitHub Copilot copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

skills CLI

$ npx skills add LanternOps/breeze --skill agent-log-debugging -a opencode

OpenCode documents no install command of its own. Project install goes to .agents/skills/; add -g for ~/.config/opencode/skills/.

GitHub CLI

$ gh skill install LanternOps/breeze agent-log-debugging --agent opencode

Project scope by default (.agents/skills/); add --scope user for a personal install.

Manual copy

$ git clone --depth 1 https://github.com/LanternOps/breeze.git skills-src && mkdir -p .opencode/skills && cp -r skills-src/.claude/skills/agent-log-debugging .opencode/skills/agent-log-debugging && rm -rf skills-src

Use ~/.config/opencode/skills/ instead of .opencode/skills for a personal install.

OpenCode skills documentation · loads skills from .opencode/skills/, .claude/skills/, .agents/skills/

Paste into OpenCode

Install the "agent-log-debugging" agent skill from https://github.com/LanternOps/breeze/tree/main/.claude/skills/agent-log-debugging into .opencode/skills/agent-log-debugging/ in this project. Copy the whole folder (SKILL.md and every file beside it), keep the folder name "agent-log-debugging", then confirm the skill loads.

OpenCode copies the folder itself, the same result as the manual copy. Check what it changed before you commit it.

Facts

Skill name: agent-log-debugging
GitHub stars: 130
Token cost: ~1.6k tokens
SKILL.md length: 408 words
Files: 1
Skills in repo: 14
Repo updated: Oct 7, 2026
First seen: Oct 7, 2026
Licence: AGPL-3.0

At a glance

A skill your agent uses when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs.

Debugging agent issues
SKILL.md covers Overview, Quick Reference and Dev Push (Build & Deploy)
Calls docker and make; needs BREEZE_API_KEY and AUTH_TOKEN
Investigating agent errors

What it does

Agent Log Debugging is an agent skill from LanternOps/breeze. Use when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs. Use when asked to check what an agent is doing or why it is failing.

Its SKILL.md is about 1.6k tokens, which your agent loads only when the skill is triggered. It is a single SKILL.md file with no bundled scripts.

It sits in Development, covering Debugging. The repository describes itself as: The open-source IT platform that comes with the workers. RMM + PSA in one system, with a governed AI operator built in. The licence is AGPL-3.0.

When your agent uses it

Debugging agent issues
Investigating agent errors
Checking agent connectivity
Reviewing agent diagnostic logs

Example prompts

“/agent-log-debugging”

Requirements

Docker
A credential in BREEZE_API_KEY
A credential in AUTH_TOKEN

What it can do on your machine

Read from SKILL.md and the folder at commit 1f72bb7. It shows what the files ask for, not the result of running them.

Tool permissions
Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.
From allowed-tools in the SKILL.md frontmatter.
Runs code
Shell commands in SKILL.md call:
- docker
- make
From the folder's file list and the shell code blocks in SKILL.md.
Network
No URLs in SKILL.md. Its commands use docker, which can reach the network depending on how they are called.
From URLs in SKILL.md, links to its own repository left out.
Credentials
Names these keys or tokens, usually read from environment variables:
- BREEZE_API_KEY
- AUTH_TOKEN
From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Agent Log Debugging loads about 1.6k tokens when it runs. Until then it costs about 54 tokens; SKILL.md has 408 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it: ~54
When it runs · the whole SKILL.md, loaded when a task matches: ~1.6k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check: notes

The automated check noted patterns worth knowing about, such as sudo or a known installer.

NoteMentions a .env fileSKILL.md:119

Defaults are read from `/.env.dev` (gitignored). Just run:

NoteMentions a .env fileSKILL.md:126
```
### .env.dev format
```

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

The full file from LanternOps/breeze at commit 1f72bb7, republished under its AGPL-3.0 licence (© LanternOps). 408 words, ~1,552 tokens.

Download SKILL.mdSave it as .claude/skills/agent-log-debugging/SKILL.md (or your agent's skills folder).

name: agent-log-debugging
description: Use when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs. Use when asked to check what an agent is doing or why it is failing.

Agent Log Debugging

Overview

Query agent diagnostic logs directly via Postgres in Docker. No API auth needed — just docker exec + psql.

Quick Reference

Direct SQL (fastest)

bash

docker exec breeze-postgres-dev psql -U breeze -d breeze -c "SQL HERE"

Common queries:

sql

-- Recent errors for a device
SELECT timestamp, level, component, message, fields
FROM agent_logs
WHERE device_id = 'DEVICE_UUID'
  AND level IN ('error', 'warn')
ORDER BY timestamp DESC LIMIT 50;

-- All logs for a device in last hour
SELECT timestamp, level, component, message
FROM agent_logs
WHERE device_id = 'DEVICE_UUID'
  AND timestamp > now() - interval '1 hour'
ORDER BY timestamp DESC;

-- Search by message text
SELECT timestamp, level, component, message, fields
FROM agent_logs
WHERE message ILIKE '%connection%'
ORDER BY timestamp DESC LIMIT 30;

-- Logs by component (updater, heartbeat, websocket, main, etc.)
SELECT timestamp, level, message, fields
FROM agent_logs
WHERE device_id = 'DEVICE_UUID'
  AND component = 'websocket'
ORDER BY timestamp DESC LIMIT 50;

-- Find device_id from agent_id
SELECT id, hostname, agent_id, status
FROM devices
WHERE agent_id = 'AGENT_ID_STRING';

-- Log volume by level (health check)
SELECT level, count(*) FROM agent_logs
WHERE timestamp > now() - interval '24 hours'
GROUP BY level ORDER BY count DESC;

Enable Debug Log Shipping

Default shipping level is warn. To get all logs for debugging, send a command to the agent:

json

{
  "type": "set_log_level",
  "payload": { "level": "debug", "durationMinutes": 60 }
}

Auto-reverts to warn after the duration. Send via device commands endpoint or WebSocket.

Note: Log shipping is NOT enabled by default. The agent_logs table will be empty until the agent's log shipper is configured and the API endpoint is reachable. If logs are empty, ask the user for logs from the agent's local log file instead.

Dashboard API Endpoint

GET /api/v1/devices/:deviceId/diagnostic-logs (JWT or API key auth)

Query params: ?level=warn,error, ?component=updater, ?since=ISO, ?until=ISO, ?search=keyword, ?page=1&limit=100

Agent Log File Locations

Platform	Path
Windows	`C:\ProgramData\Breeze\logs\agent.log`
Windows (user helper)	`C:\ProgramData\Breeze\logs\user-helper.log`
macOS	`/Library/Application Support/Breeze/logs/agent.log`
Linux	`/var/log/breeze/agent.log`

Configurable via log_file in agent.yaml. Rotated at 50MB, 3 backups.

Log Shipping Pipeline

Agent slog handler → Shipper.Enqueue() → buffer (1000 entries) → batch every 60s → gzip POST to POST /api/v1/agents/:agentId/logs → agent_logs table

Key Tables

agent_logs — shipped diagnostic logs (level, component, message, fields, agent_version)
devices — lookup device_id from agent_id
device_commands — command history (check if set_log_level was sent)

Common Debug Scenarios

Symptom	Query
Agent not connecting	Filter component=`websocket`, level=`error`
Heartbeat failures	Filter component=`heartbeat`, level=`error`
Update failures	Filter component=`updater`
mTLS issues	Search message `mTLS` or `certificate`
Agent crash loop	Check log volume spike + last messages before gap
Remote desktop black screen	Filter component=`heartbeat` or `sessionbroker`, check for IPC/helper messages
Helper disconnect	Check `user-helper.log` on device for timeout/IPC errors

Show full SKILL.md (150 more words)Show less

Dev Push (Build & Deploy)

Zero-arg dev-push (recommended)

Defaults are read from /.env.dev (gitignored). Just run:

bash

cd agent
make dev-push

.env.dev format

BREEZE_API_KEY=brz_...
BREEZE_DEV_DEVICE=<device-uuid>
BREEZE_API_URL=http://<your-dev-host>:3001

Override any default

bash

make dev-push DEVICE=<other-device> AUTH_TOKEN=<other-key> API_URL=<other-url>

Auth: JWT or API key

The Makefile auto-detects brz_ prefix and sends via X-API-Key header. JWTs are sent via Authorization: Bearer. The dev-push API endpoint (POST /api/v1/dev/push) accepts both.

Current dev environment

Item	Value
Device ID	`<device-uuid>`
Agent ID	`<agent-id>`
Hostname	`<your-dev-host>`
API URL	`http://<your-dev-host>:3001`
Platform	windows/amd64

Dev Iteration Loop: Fetch Logs → Fix → Deploy → Check

When debugging agent issues, use this cycle with dev push to iterate fast:

1. FETCH LOGS — identify the problem
   docker exec breeze-postgres-dev psql -U breeze -d breeze -c "
     SELECT timestamp, level, component, message
     FROM agent_logs
     WHERE device_id = '<device-uuid>'
       AND level IN ('error','warn')
     ORDER BY timestamp DESC LIMIT 30;"

   If agent_logs is empty, ask user for local log file contents.

2. FIX CODE — edit Go source in agent/internal/...

3. BUILD & DEPLOY — push new binary (agent restarts in ~5s)
   cd agent
   make dev-push

4. CHECK LOGS — verify the fix landed
   docker exec breeze-postgres-dev psql -U breeze -d breeze -c "
     SELECT timestamp, level, component, message, fields
     FROM agent_logs
     WHERE device_id = '<device-uuid>'
       AND timestamp > now() - interval '2 minutes'
     ORDER BY timestamp DESC;"

   → Confirm new agent_version shows 'dev-<timestamp>'
   → Confirm error/warn messages are gone
   → If not fixed, loop back to step 1

Tips:

Before starting, bump log level: send set_log_level command with {level: "debug", durationMinutes: 30} so you get full detail
After dev-push, auto_update is disabled on the agent — re-enable in agent.yaml when done
The dev push binary includes the version string dev-<unix-timestamp> — filter by agent_version in logs to confirm which build is running
Dev push only works in non-production (NODE_ENV !== 'production' or DEV_PUSH_ENABLED=true)

Files

Just SKILL.md in .claude/skills/agent-log-debugging of LanternOps/breeze.

Open the folder on GitHubat commit 1f72bb7

Compare with similar skills

Agent Log Debugging next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Agent Log Debugging compared with similar skills
Skill	Stars	Used in	Tokens	Auto-check	Licence	Repo updated
Agent Log Debugging this skillLanternOps/breeze	130	—	~1.6k	Automated safety check: Notes	AGPL-3.0	today
Native Data FetchingCherryHQ/cherry-studio-app	4k	6 repos	~2.9k	Automated safety check: Notes	MIT	4 days ago
Gumroad Prod Consoleantiwork/gumroad	9.8k	—	~2.9k	Automated safety check: Notes	MIT	today
LangBot Plugin Developmentlangbot-app/LangBot	18k	—	~3.9k	Automated safety check: Pass	Apache-2.0	today
Keybase RPC Log Analysiskeybase/client	9.3k	—	~3k	Automated safety check: Pass	BSD-3-Clause	today
Jazz UI Developmentgarden-co/classic-jazz	2.5k	—	~1.7k	Automated safety check: Pass	MIT	1 mo ago

Similar skills

Native Data Fetching
CherryHQ/cherry-studio-app
A skill your agent uses when implementing or debugging ANY network request, API call, or data fetching.
4k GitHub starsUsed in 6 repos~2.9k tokens
DevelopmentAuto-check: notes
Gumroad Prod Console
antiwork/gumroad
Execute read-only Ruby/Rails commands against Gumroad's production database for debugging and investigation.
9.8k GitHub stars~2.9k tokensUpdated today
DevelopmentAuto-check: notes
LangBot Plugin Development
langbot-app/LangBot
Guides building, debugging and testing LangBot plugins: components, SDK calls, README and locale rules, SDK pitfalls and WebSocket-based testing.
18k GitHub stars~3.9k tokensUpdated today
DevelopmentAuto-check passed
Keybase RPC Log Analysis
keybase/client
Captures a clean Keybase service log and analyzes it for redundant, duplicated or looping RPCs, then checks whether a caching fix reduced the calls.
9.3k GitHub stars~3k tokensUpdated today
DevelopmentAuto-check passed
Jazz UI Development
garden-co/classic-jazz
A skill your agent uses when building, debugging, or optimizing Jazz applications.
2.5k GitHub stars~1.7k tokensUpdated 1 mo ago
DevelopmentAuto-check passed
Logging Patterns
decebals/claude-code-java
Java logging best practices with SLF4J, structured logging (JSON), and MDC for request tracing.
750 GitHub starsUsed in 1 repo~3.3k tokens
DevelopmentAuto-check passed

Questions about Agent Log Debugging

What does Agent Log Debugging do?

A skill your agent uses when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs. Agent Log Debugging is an agent skill from LanternOps/breeze. Use when debugging agent issues, investigating agent errors, checking agent connectivity, or reviewing agent diagnostic logs.

When should I use Agent Log Debugging?

Agent Log Debugging fits situations like: debugging agent issues; investigating agent errors; checking agent connectivity; reviewing agent diagnostic logs.

How do I install Agent Log Debugging in Claude Code?

Run `npx skills add LanternOps/breeze --skill agent-log-debugging -a claude-code`. Or copy the skill folder (.claude/skills/agent-log-debugging in LanternOps/breeze) into .claude/skills/agent-log-debugging in your project. Claude Code loads it when a task matches its description.

How do I install Agent Log Debugging in Codex?

Run `npx skills add LanternOps/breeze --skill agent-log-debugging -a codex`. Or copy the skill folder (.claude/skills/agent-log-debugging in LanternOps/breeze) into .agents/skills/agent-log-debugging in your project. Codex loads it when a task matches its description.

Can I use Agent Log Debugging in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add LanternOps/breeze --skill agent-log-debugging -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/agent-log-debugging, .gemini/skills/agent-log-debugging, .github/skills/agent-log-debugging and .opencode/skills/agent-log-debugging in your project.

What does Agent Log Debugging need to run?

Going by SKILL.md and its folder, Agent Log Debugging needs the command-line tools its instructions call (docker and make) and credentials named BREEZE_API_KEY and AUTH_TOKEN. Our summary lists: Docker; A credential in BREEZE_API_KEY; A credential in AUTH_TOKEN.

Does Agent Log Debugging access the network?

SKILL.md contains no URLs. Its commands use docker, which can reach the network depending on how they are called. This is read from the text; nothing was executed.

Is Agent Log Debugging safe to install?

Our automated static check of SKILL.md found notes only (mentions a .env file), nothing it rates as a warning. It is not a guarantee. Review the folder before installing.

What licence does Agent Log Debugging use?

Agent Log Debugging is published under the AGPL-3.0 licence (the repository's licence). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Agent Log Debugging use?

About 1.6k tokens (SKILL.md is roughly 6.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Agent Log Debugging?

Skills that share tags, products or a category with Agent Log Debugging: Native Data Fetching (CherryHQ/cherry-studio-app, 4k stars), Gumroad Prod Console (antiwork/gumroad, 9.8k stars), LangBot Plugin Development (langbot-app/LangBot, 18k stars) and Keybase RPC Log Analysis (keybase/client, 9.3k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Agent Log Debugging?

LanternOps (a GitHub organization) maintains it in LanternOps/breeze, which has 130 GitHub stars. The repository holds 14 skills in this directory. The repository was last updated on October 7, 2026.

Source: LanternOps/breeze on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.

Install Agent Log Debugging

Facts

At a glance

What it does

When your agent uses it

Example prompts

Requirements

What it can do on your machine

Tool permissions

Runs code

Network

Credentials

Context cost

Safety

SKILL.md

Agent Log Debugging

Overview

Quick Reference

Direct SQL (fastest)

Enable Debug Log Shipping

Dashboard API Endpoint

Agent Log File Locations

Log Shipping Pipeline

Key Tables

Common Debug Scenarios

Dev Push (Build & Deploy)

Zero-arg dev-push (recommended)

.env.dev format

Override any default

Auth: JWT or API key

Current dev environment

Dev Iteration Loop: Fetch Logs → Fix → Deploy → Check

Files

Compare with similar skills

Similar skills

More from LanternOps/breeze

Related

Questions about Agent Log Debugging