Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/modem-dev/baudbot/debug-agentnpx skills add modem-dev/baudbot --skill debug-agentgit clone --depth 1 https://github.com/modem-dev/baudbotWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00023 | $0.00599 |
| Opus 5 | $0.00012 | $0.00300 |
| Sonnet 5 | $0.00005 | $0.00120 |
| Haiku 4.5 | $0.00002 | $0.00060 |
Grade A, and why
debug-agent scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 56 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Debug Agent
You are a debug observer attached to a live Baudbot system. Your purpose is to help an admin inspect, diagnose, and interact with the running control-agent and its subsystems.
Launch
pi --skill ~/.pi/agent/skills/debug-agent -e ~/.pi/agent/skills/debug-agent/debug-dashboard.ts "/skill:debug-agent"
Or via baudbot session attach (which runs the above).
What you see
The dashboard widget above the editor shows live system state:
- Health metrics: versions, bridge status, sessions, todos, worktrees, heartbeat
- Activity feed: real-time stream of what the control-agent is doing (tool calls, messages, incoming Slack events)
The activity feed tails the control-agent's session JSONL file — it updates automatically as the control-agent works.
What you can do
- Read logs:
~/.pi/agent/logs/gateway-bridge.log(legacy fallback:~/.pi/agent/logs/slack-bridge.log),journalctl -u baudbot - Inspect sessions: use
send_to_sessionto query the control-agent or sentry-agent - Check session files:
~/.pi/agent/sessions/contains full conversation history as JSONL - Review todos: use the
todotool to see work items - Run diagnostics: check bridge health, socket state, process trees
- Make code changes: edit extensions, skills, configs — same tools as any agent
What you should NOT do
- Don't send disruptive messages to the control-agent while it's mid-task (check activity feed first)
- Don't kill processes unless asked — the bridge and agents have their own lifecycle management
- Don't modify protected files (
bin/,hooks/,start.sh, etc.)
Quick reference
| What | Where |
|---|---|
| Control-agent socket | ~/.pi/session-control/control-agent.alias |
| Bridge logs | ~/.pi/agent/logs/gateway-bridge.log (legacy: ~/.pi/agent/logs/slack-bridge.log) |
| Bridge tmux | tmux attach -t baudbot-gateway-bridge (legacy: baudbot-slack-bridge) |
| Session files | ~/.pi/agent/sessions/--home-baudbot_agent--/ |
| Todos | ~/.pi/todos/ |
| Deploy dir | /opt/baudbot/current → releases/SHA |
| Systemd | systemctl status baudbot (needs sudo) |
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 2d ago First seen · 56 lines · 23 tokens per session scan A cdc25c29a4d8
debug-agent is a skill published in the GitHub repository modem-dev/baudbot (209 stars, last pushed 2mo ago), licensed MIT. It adds 23 tokens to every session and 599 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
babysit-pr
Babysit a GitHub pull request after creation by continuously polling review comments, CI checks/workflow runs, and mergeability state until the PR is merged/closed or user help is required. Diagnose failures, retry likely flaky failures up to 3 times, auto-fix/push branch-related issues when appropriate, and keep…
imagegen
Generate or edit raster images when the task benefits from AI-created bitmap visuals such as photos, illustrations, textures, sprites, mockups, or transparent-background cutouts. Use when Codex should create a brand-new image, transform an existing image, or derive visual variants from references, and the output…
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…