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/starter-series/create-starter/deploy-setupnpx skills add starter-series/create-starter --skill deploy-setupgit clone --depth 1 https://github.com/starter-series/create-starterWhat 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 | $0.00061 | $0.02119 |
| Opus 5 | $0.00030 | $0.01059 |
| Sonnet 5 | $0.00012 | $0.00424 |
| Haiku 4.5 | $0.00006 | $0.00212 |
Grade A, and why
deploy-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 yesterday.
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 — 143 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are walking a developer through the first deploy of a Starter Series project. The project has been scaffolded (via create-starter skill / CLI / MCP) and is on disk; this skill takes it from "scaffolded" to "first release published."
Prerequisites
- The project is already scaffolded and on disk. Verify by checking for
.github/workflows/cd*.ymlandpackage.json/pyproject.toml/Dockerfile. ghCLI is installed and authenticated (gh auth status). If not, instruct the user.- A GitHub repository exists for the project. If not, offer
gh repo create.
Workflow
Step 1: Detect the template
Read these files to identify which starter the project came from:
| Signal | Template |
|---|---|
package.json#mcpName starts with io.github. and package.json#main exists, no electron dep |
mcp-server (Node MCP) |
pyproject.toml references mcp package |
mcp-server-python |
package.json#dependencies.discord.js |
discord-bot |
package.json#dependencies.grammy |
telegram-bot |
manifest.json#manifest_version === 3 |
browser-extension |
package.json#engines.vscode |
vscode-extension |
package.json#dependencies.electron (or devDependencies.electron) |
electron-app |
package.json#dependencies.expo |
react-native |
wrangler.toml exists |
cloudflare-pages |
Dockerfile at root + no package.json |
docker-deploy |
package.json#publishConfig.access === "public" and no other signal |
npm-package |
Report the detected template name to the user.
Step 2: Inspect the CD workflow
Read .github/workflows/cd.yml (or cd-android.yml + cd-ios.yml for react-native, or cd-firefox.yml for browser-extension). Extract:
- The list of
secrets.Xreferenced inwith:/env:/if:blocks. These are the secrets that must be set. - Whether the workflow uses OIDC trusted publishing (look for
id-token: writeinpermissions:andnpm publish --provenance/pypa/gh-action-pypi-publishin steps). If yes, the publish step needs no token secret — only registry-side configuration (web UI). If no, a token secret is required.
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.
- yesterday First seen · 143 lines · 61 tokens per session scan A e7e375148d53
deploy-setup is a skill published in the GitHub repository starter-series/create-starter (1 stars, last pushed 14d ago), licensed MIT. It adds 61 tokens to every session and 2,119 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 2026-08-31.
Other skills, from other repositories
skill-creator
Create new bb skills and improve existing ones. Use whenever a user asks to create, write, edit, refine, test, or optimize a skill; turn a workflow into a reusable skill; fix skill triggering; or improve a SKILL.md file.
local-ci-dev
Run local CI via the in-tree dev build of local-ci (pnpm local-ci-dev) to verify changes to this repo before completing work. Runs pnpm local-ci-dev run --all in the background, watches the log for step failures, and retries failed runners after fixes. Use before reporting work as complete, or whenever the user asks…
local-ci
Run GitHub Actions workflows locally with pause-on-failure for AI-agent-driven CI iteration.
local-ci
Run GitHub Actions CI locally with Local CI to validate changes before pushing. Use when testing, running checks, or validating code changes.
calibrate-subagents
Audits every subagent .md across user / project / plugin-self / plugin-cache. Flags missing frontmatter (name, description, tools), the big footgun (no tools: → inherits ALL tools including every MCP server), bodies over 200 lines, omitted model: (defaults to inherit, silently inflates cost), vague descriptions Claude…
skill-creator
Create new skills, modify and improve existing skills, and measure skill performance. Use when users want to create a skill from scratch, edit, or optimize an existing skill, run evals to test a skill, benchmark skill performance with variance analysis, or optimize a skill's description for better triggering accuracy.