agentmods.dev

add-to-project

add-to-project is a skill for Claude Code from Marve10s/Better-Fullstack. It costs 71 tokens per session (451 once invoked), scanned A, original, MIT.

A project-update workflow for an existing Better Fullstack project, identified by a bts.jsonc file. It plans changes to the project’s capabilities, services, deployment targets, and generated files before applying them.

In plain words
What is it for?
Use it to add capabilities such as CI, documentation, email, search, storage, rate limiting, or mobile support. It also helps plan riskier changes to databases, authentication, APIs, payments, or other stack parts.
Why use it?
It reduces the risk of changing generated project files by hand or choosing incompatible updates. A preview shows blockers, file and dependency changes, environment changes, and compatibility adjustments first.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin.

Part of the better-fullstack plugin — 2 skills, 1 MCP server shipped together

not rated 729 changed 2d ago A scan 71 tokens original MIT
View the source file Marve10s/Better-Fullstack better-fullstack.dev
Install

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.

agentmods
npx agentmods add skills/marve10s/better-fullstack/add-to-project
Any agent
npx skills add Marve10s/Better-Fullstack --skill add-to-project
Clone the repo
git clone --depth 1 https://github.com/Marve10s/Better-Fullstack

Made for: Claude Code.

Or install better-fullstack, the plugin that ships this one along with the rest of its 2 skills, 1 MCP server.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for add-to-project

README.md
[![agentmods](https://agentmods.dev/badge/skills/marve10s/better-fullstack/add-to-project.svg)](https://agentmods.dev/skills/marve10s/better-fullstack/add-to-project)
Your own site
<a href="https://agentmods.dev/skills/marve10s/better-fullstack/add-to-project"><img src="https://agentmods.dev/badge/skills/marve10s/better-fullstack/add-to-project.svg" alt="Measured on agentmods" height="20"></a>
Per session 71 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 451 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00071 $0.00451
Opus 5 $0.00036 $0.00226
Sonnet 5 $0.00014 $0.00090
Haiku 4.5 $0.00007 $0.00045

Measured 2d ago against content hash 8dda945ce63b, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

add-to-project 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.

plugin/skills/add-to-project/SKILL.md · 43 lines

What it actually says

Add to an Existing Better Fullstack Project

Use the Better Fullstack MCP server for existing-project updates. Do not hand-edit generated stack metadata or guess which template files belong to a capability.

Workflow

  1. Confirm the project directory and ensure it contains bts.jsonc.
  2. Call bfs_get_guidance and bfs_get_schema.
  3. For capability changes, call bfs_plan_stack_update with the target projectDir and requested stack fields.
  4. Review the preview, including blockers, file changes, dependency changes, env changes, and compatibility adjustments.
  5. Call bfs_apply_stack_update only when the plan is acceptable.
  6. For legacy addon/deploy-only changes, call bfs_plan_addition before bfs_add_feature.
  7. Report changed files and the exact install/test commands.

Rules

  • Keep update semantics preview-first.
  • Prefer additive updates first: generated CI, docs, observability, email, search, vector DB, file storage, rate limiting, and mobile capabilities.
  • Treat database, ORM, auth, API, and payment-provider swaps as risky and make compatibility changes explicit.
  • Set installs disabled unless the user asks for dependency installation.
  • Do not start a dev server.

CLI-only fallback

If the Better Fullstack MCP tools are unavailable, inspect the current flags with npx -y create-better-fullstack@latest add --help, then run the explicit add command with --project-dir <path> --dry-run --no-install. Review that preview before rerunning without --dry-run. Do not guess option names or hand-edit generated stack metadata.

Changes

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.

  1. 2d ago Changed · +7 lines 8dda945ce63b
  2. 6d ago First seen · 36 lines · 71 tokens per session scan A 4ee12c69b53b

Subscribe to this mod's changes

add-to-project is a skill published in the GitHub repository Marve10s/Better-Fullstack (729 stars, last pushed yesterday), licensed MIT. It adds 71 tokens to every session and 451 once invoked, about $0.0004 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.

DevOps and cloudGoRustTypeScriptclidrizzle-ormfull-stack
Related

Other skills, from other repositories

review-pr

Review a Deno runtime pull request for correctness, tests, security, and conventions. Use when asked to review a PR or when a PR number/URL is provided for review.

denoland/deno · 39 tokens

node-compat

Run a Node.js compatibility test, diagnose failures, and either fix the implementation, skip, or ignore the test. Use when asked to work on node compat tests.

denoland/deno · 37 tokens

fmt

Format all code in the repository. Run before opening a PR or committing changes.

denoland/deno · 18 tokens

lint-all

Lint all code (Rust + JS/TS). Use before opening a PR when Rust code was changed.

denoland/deno · 24 tokens

lint-js

Lint JS/TS code only. Use before opening a PR when only JavaScript or TypeScript files were changed (no Rust).

denoland/deno · 29 tokens

go-rust-reverse

Use for reverse engineering stripped Go and Rust binaries including runtime recognition, pclntab/moduel data recovery, panic strings, and idiomatic decompilation recovery.

zhaoxuya520/reverse-skill · 38 tokens