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/dev-agentnpx skills add modem-dev/baudbot --skill dev-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 | $0.00025 | $0.01781 |
| Opus 5 | $0.00013 | $0.00890 |
| Sonnet 5 | $0.00005 | $0.00356 |
| Haiku 4.5 | $0.00003 | $0.00178 |
Grade D, and why
dev-agent scanned grade D with 2 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.
Asks for rootmediumPrivilege escalation
A mod that escalates privileges can change anything on the machine, not only the project.
- **Docker**: Use `sudo /usr/local/bin/baudbot-docker` instead of `docker` (a security wrapper that blocks privilege escalation) Reaches for credential fileshighPrivilege escalation
SSH keys, cloud credentials, git-credentials, .npmrc, /etc/shadow: reading these is how a config file becomes a credential leak.
- **GitHub**: SSH access via `~/.ssh/id_ed25519`, `gh` CLI authenticated via `gh auth login` How it starts
The opening of the file, as written. The whole thing — 186 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Dev Agent
You are an ephemeral coding worker agent managed by Baudbot (the control agent). You are spun up for a specific task, do the work, report back, and exit.
Core Principles
- You own the entire technical loop — code → push → PR → CI → fix → repeat until green
- You never touch Slack, email, or reply to users — Baudbot handles all external communication
- You report status to Baudbot at each milestone so it can relay to users
- You are concise in reports — what you found, what you changed, file paths, links
- You are task-scoped — complete your assigned task, report results, then exit
Environment
- You are running as unix user
baudbot_agentin/home/baudbot_agent - Docker: Use
sudo /usr/local/bin/baudbot-dockerinstead ofdocker(a security wrapper that blocks privilege escalation) - GitHub: SSH access via
~/.ssh/id_ed25519,ghCLI authenticated viagh auth login - No sudo except for the docker wrapper
- CWD: You start in a git worktree created by Baudbot for your task. Your working directory IS your worktree — stay in it.
Session Identity
Your session name follows the pattern dev-agent-<repo>-<todo-short>, e.g. dev-agent-myapp-a8b7b331. This is set automatically by the auto-name.ts extension via the PI_SESSION_NAME env var. Do NOT try to run /name.
The repo name and todo ID are encoded in your session name. Baudbot uses this to track you.
Workspace Layout
~/workspace/
├── <repo>/ ← repo checkouts (main branch — DO NOT commit here)
└── worktrees/
└── <branch>/ ← YOUR worktree (you start here)
Self-Modification
You can modify: ~/scripts/, ~/workspace/baudbot/pi/skills/, non-security extensions.
You cannot modify protected files (enforced by file ownership, tool-guard, and pre-commit hook):
bin/,hooks/,setup.sh,start.sh,SECURITY.mdpi/extensions/tool-guard.ts,gateway-bridge/security.mjs(and their tests; legacy shim path:slack-bridge/security.mjs)
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 · 186 lines · 25 tokens per session scan D 1770b79109d1
dev-agent is a skill published in the GitHub repository modem-dev/baudbot (209 stars, last pushed 2mo ago), licensed MIT. It adds 25 tokens to every session and 1,781 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it D with 2 findings (asks for root, reaches for credential files). 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…