scan-projects

A scanner that searches a configured directory for software projects and writes the results to a Markdown file for review. It recognizes common project files, Git repositories, and Docker or Docker Compose files.

In plain words
What is it for?
Use it to scan up to four directory levels, identify likely project roots, and create a projects-list.md file for manual filtering.
Why use it?
It gives you one inventory of projects instead of requiring you to find them by hand.

Cursor rule

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 rules/jasonchen0604/codebase-to-portfolio/scan-projects
Clone the repo
git clone --depth 1 https://github.com/jasonChen0604/codebase-to-portfolio
Per session 59 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,394 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 $0.00059 $0.01394
Opus 5 $0.00030 $0.00697
Sonnet 5 $0.00012 $0.00279
Haiku 4.5 $0.00006 $0.00139

Measured 2d ago against content hash 36d22fcf2bbe, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan-projects 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.

adapters/cursor/scan-projects.mdc · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Scan Projects Skill

Goal

Scan all valid software projects under the configured scan_root and output a Markdown report (projects-list.md) for manual filtering.

Step 0: Read config

Read profile.config.json from the current working directory. If missing, tell the user to copy examples/profile.config.example.json to profile.config.json and fill it in, then stop.

  • scan_root (default ~/project if not set) — expand ~ to $HOME
  • A user-specified path argument overrides scan_root for this run

Definition of a Valid Software Project

A directory is considered a valid project root if any of the following markers exist (file or directory):

package.json, Cargo.toml, go.mod, pyproject.toml, requirements.txt, setup.py,
Makefile, pom.xml, build.gradle, CMakeLists.txt, .git, composer.json, Gemfile,
Dockerfile, dockerfile, docker-compose.yml, docker-compose.yaml, compose.yml, compose.yaml

Execution Steps

Step 1: Confirm scan root directory

  • Use scan_root from config (or the user-specified override)
  • Verify the directory exists with ls

Step 2: Execute scan (recursive, max 4 levels)

  • If the current directory matches any marker → treat as project root, do not recurse further
  • If no match → continue scanning subdirectories, max depth of 4
  • Skip the following subdirectory names: node_modules, .git, .venv, __pycache__, dist, build, packages

Use the following bash script:

BASE_DIR="<scan_root, ~ expanded to $HOME>"
MAX_DEPTH=4
MARKERS=(
  "package.json" "Cargo.toml" "go.mod" "pyproject.toml" "requirements.txt"
  "setup.py" "Makefile" "pom.xml" "build.gradle" "CMakeLists.txt" ".git"
  "composer.json" "Gemfile" "Dockerfile" "dockerfile"
  "docker-compose.yml" "docker-compose.yaml" "compose.yml" "compose.yaml"
)

is_project_root() {
  local dir="$1"
  for marker in "${MARKERS[@]}"; do
    [[ -e "$dir/$marker" ]] && return 0
  done
  return 1
}

collect_projects() {
  local dir="$1"
  local depth="$2"
  [[ "$depth" -gt "$MAX_DEPTH" ]] && return

  if is_project_root "$dir"; then
    echo "$dir"
    return
  fi

  while IFS= read -r subdir; do
    collect_projects "$subdir" $(( depth + 1 ))
  done < <(find "$dir" -mindepth 1 -maxdepth 1 -type d \
    ! -name "node_modules" ! -name ".git" ! -name ".venv" \
    ! -name "__pycache__" ! -name "dist" ! -name "build" ! -name "packages")
}

collect_projects "$BASE_DIR" 0

Read the full file on GitHub · 123 lines

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 First seen · 123 lines · 59 tokens per session scan A 36d22fcf2bbe

Subscribe to this mod's changes

scan-projects is a cursor rule published in the GitHub repository jasonChen0604/codebase-to-portfolio (2 stars, last pushed 1mo ago), licensed MIT. It adds 59 tokens to every session and 1,394 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.