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/bdfinst/agentic-dev-team/cloud-setupnpx skills add bdfinst/agentic-dev-team --skill cloud-setupgit clone --depth 1 https://github.com/bdfinst/agentic-dev-teamWhat 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 | $0.00070 | $0.00746 |
| Opus 5 | $0.00035 | $0.00373 |
| Sonnet 5 | $0.00014 | $0.00149 |
| Haiku 4.5 | $0.00007 | $0.00075 |
Grade A, and why
cloud-setup 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.
What it actually says
Cloud sessions (claude.ai/code)
Plugins are a local CLI / IDE feature. A Claude Code web session runs in a fresh managed VM that clones this repo; setup scripts and env vars are set in the cloud UI (not a repo file) — see Claude Code on the web.
Install the plugin via the Setup script (loads this session). Claude
loads all skills, agents, and commands once when it starts, so the plugin must
be on disk before Claude launches. The environment Setup script (cloud UI) runs
pre-boot and its filesystem is snapshotted and reused — installing the plugin
there makes it load in the same session. The claude CLI is available in
cloud environments. Paste the body of .claude/cloud-setup.sh
into the Setup script field; it installs the toolchain and then the plugin
(claude plugin marketplace add bdfinst/agentic-dev-team +
claude plugin install dev-team@bfinster), always exiting 0. See
docs/cloud-setup.md for the focused recipe, the exact
snippet, and the verification probe.
SessionStart hook is a fallback only — it lands next session.
.claude/settings.json registers a SessionStart hook
(.claude/install-dev-team.sh), gated to DEV_TEAM_CLOUD_INSTALL=1 (set it
in Environment variables; leave it unset locally). Because the hook runs after
boot, the plugin it installs only takes effect on the next session — use the
Setup script for same-session loading.
If a network policy blocks the install, use the plugin's files directly. The skills and agents are plain files in this repo; run any workflow manually:
- a skill →
plugins/dev-team/skills/<name>/SKILL.md(e.g./plan→ readplugins/dev-team/skills/plan/SKILL.mdand follow its steps); - a review agent →
plugins/dev-team/agents/<name>.md; - the catalog →
plugins/dev-team/knowledge/agent-registry.md.
Test tooling in cloud. The same .claude/cloud-setup.sh that installs the
plugin also installs this repo's gates (jq, shellcheck, the Python
dev deps, and gh) — one paste into the Setup script field covers both. There
is no dedicated secrets store yet — treat env vars as visible to anyone who can
edit the environment.
For the full walkthrough of running a plugin's skills from a web session (the
Setup-script install plus the file-based fallback), see
docs/cloud-setup.md and
docs/using-plugin-skills-in-the-web-environment.md.
See plugins/dev-team/CLAUDE.md for the full orchestration pipeline configuration.
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 · 52 lines · 70 tokens per session scan A b1b1273b638b
cloud-setup is a skill published in the GitHub repository bdfinst/agentic-dev-team (277 stars, last pushed yesterday), licensed MIT. It adds 70 tokens to every session and 746 once invoked, about $0.0003 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…