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/jasonchen0604/codebase-to-portfolio/scan-projectsnpx skills add jasonChen0604/codebase-to-portfolio --skill scan-projectsgit clone --depth 1 https://github.com/jasonChen0604/codebase-to-portfolioWrote 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.
[](https://agentmods.dev/skills/jasonchen0604/codebase-to-portfolio/scan-projects)<a href="https://agentmods.dev/skills/jasonchen0604/codebase-to-portfolio/scan-projects"><img src="https://agentmods.dev/badge/skills/jasonchen0604/codebase-to-portfolio/scan-projects.svg" alt="Measured on agentmods" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00063 | $0.01394 |
| Opus 5 | $0.00032 | $0.00697 |
| Sonnet 5 | $0.00013 | $0.00279 |
| Haiku 4.5 | $0.00006 | $0.00139 |
Grade A, and why
scan-projects scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Scan Projects Skill
Goal
Scan all valid software projects under the configured scan_root and output a Markdown report (projects-list.md) for manual filtering.
Step 0: Read config
Read profile.config.json from the current working directory. If missing, tell the user to copy examples/profile.config.example.json to profile.config.json and fill it in, then stop.
scan_root(default~/projectif not set) — expand~to$HOME- A user-specified path argument overrides
scan_rootfor 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_rootfrom 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
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.
- 4d ago First seen · 122 lines · 63 tokens per session scan A 4e9bc4e87b18
scan-projects is a skill published in the GitHub repository jasonChen0604/codebase-to-portfolio (2 stars, last pushed 1mo ago), licensed MIT. It adds 63 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.
Other skills, from other repositories
jira-bug-reporter
Create detailed bug reports from session evidence — auto-populate Jira tickets with session URLs, error messages, device info, and reproduction steps. Use when the user wants to file a bug from a Fullstory session.
retro
CP-7 retrospective: audit checkpoints, evidence quality, action items, and harvest candidates. Closes the V-model cycle and feeds the next run. Use via /retro after ship, escalate, or significant session.
pad
Talk to your project. Natural-language project management — create items, check status, plan work, brainstorm ideas, and more.
fde
Keeps the engagement record for client work. Use when they name a client or stakeholder. Use when they debrief a meeting or paste notes. Use when they ask what was agreed. Use when they run a POC, change the client's codebase, prove it on their staging, go live, or need evals before a model acts. Use when they prep a…
pm-arch
Skill "pm-arch" from wei63w/pm-manager, covering user input, outline, done when and shared workflow (all /pm- commands).
pm-all
Skill "pm-all" from wei63w/pm-manager, covering user input, outline and shared workflow (all /pm- commands).