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.
git 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/rules/jasonchen0604/codebase-to-portfolio/init-project-doc)<a href="https://agentmods.dev/rules/jasonchen0604/codebase-to-portfolio/init-project-doc"><img src="https://agentmods.dev/badge/rules/jasonchen0604/codebase-to-portfolio/init-project-doc/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/rules/jasonchen0604/codebase-to-portfolio/init-project-doc"><img src="https://agentmods.dev/badge/rules/jasonchen0604/codebase-to-portfolio/init-project-doc.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00075 | $0.01591 |
| Opus 5.5 | $0.00030 | $0.00636 |
| Sonnet 5.5 | $0.00015 | $0.00318 |
| Haiku 4.5 | $0.00007 | $0.00159 |
Grade A, and why
init-project-doc 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 2mo 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 — 112 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Init Project Doc Skill
Role
You are a senior software architect and personal-brand consultant. The goal is to inventory a software project so it can feed an automated personal portfolio site and resume/LinkedIn sync.
Trigger
The user provides a project's directory tree and/or core source snippets, and asks for a project doc to be generated.
Execution Steps
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.
doc_filename(defaultCLAUDE.md) — the output filenamelanguages(default["en"]) — output language(s) for descriptive texttimezone(default+00:00) — used for thegenerated_attimestamp
Step 1: Read reference files
Read the following files, located in this skill's directory:
config.json→allowed_categoriesandallowed_statusesliststemplate.md→ output format (with YAML frontmatter) and all{{VARIABLE}}fields
Step 2: Analyze project code
From the user-provided tree structure and source code, identify:
- Core language & framework (e.g. TypeScript + Next.js, Python + FastAPI)
- Database / storage layer (e.g. PostgreSQL, Redis, SQLite)
- Build tools / package manager (e.g. pnpm, Poetry, Gradle)
- Deployment / cloud services (e.g. Vercel, Docker, AWS Lambda)
- Key feature highlights (inferred from directory structure and code logic)
- Technical challenges (default to "None (fill in manually)" if not evident)
- Architecture patterns (e.g. MVC, Repository Pattern, Event-Driven)
- State management (e.g. Zustand, Redux, Context API, none)
- Auth / authorization mechanism (e.g. NextAuth, JWT, OAuth, none)
Step 3: Apply constraints
category: must exactly match one item fromallowed_categories— do not invent new onesstatus: must exactly match one item fromallowed_statuses— do not invent new onesfeatured: alwaysfalsegithub_repo_name: inferred from the project directory name (empty string if unclear)cover_image: always empty string""
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.
- 2mo ago First seen · 112 lines · 75 tokens per session scan A 6688949c002a
init-project-doc is a cursor rule published in the GitHub repository jasonChen0604/codebase-to-portfolio (2 stars, last pushed 3mo ago), licensed MIT. It adds 75 tokens to every session and 1,591 once invoked, about $0.0003 per session on Opus 5.5. 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 cursor rules, from other repositories
the-loop
If .the-loop/harness-config.yaml exists in this repository, the-loop is initialized here. Operating rules: plan → execute → self/critic-review → escalate. Read .the-loop/harness-config.yaml (the agent's config — the CLI never reads it) and follow the the-loop skill before working any ticket. If the file does not…
python
Python best practices and patterns for modern software development with Flask and SQLite.
archcore-files
Enforce MCP-only operations when working with .archcore/ files.
execution
Repository execution and verification commands.
orchestrator-main
Rules for the main orchestrator agent in multi-agent workflows.
lean
Answer densely. Cut filler, keep all technical signal.