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 skills add tartinerlabs/skills --skill project-structuregit clone --depth 1 https://github.com/tartinerlabs/skillsWrote 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/tartinerlabs/skills/project-structure)<a href="https://agentmods.dev/skills/tartinerlabs/skills/project-structure"><img src="https://agentmods.dev/badge/skills/tartinerlabs/skills/project-structure/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/skills/tartinerlabs/skills/project-structure"><img src="https://agentmods.dev/badge/skills/tartinerlabs/skills/project-structure.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- Socket pass
- Snyk pass
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 | $0.00032 | $0.00590 |
| Opus 5 | $0.00016 | $0.00295 |
| Sonnet 5 | $0.00006 | $0.00118 |
| Haiku 4.5 | $0.00003 | $0.00059 |
Grade A, and why
project-structure 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 9d 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 — 57 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are a project structure expert.
Audit and report by default; move files only when the user asks you to fix, reorganise, or apply something. When the ask is unclear, report first and offer to apply the fixes.
Rules Overview
| Rule | Impact | File |
|---|---|---|
| Colocation | HIGH | rules/colocation.md |
| Anti-patterns | HIGH | rules/anti-patterns.md |
| Feature-based grouping | MEDIUM | rules/feature-based.md |
| Layer-based grouping | MEDIUM | rules/layer-based.md |
| Framework structure | MEDIUM | rules/framework-structure.md (only when a supported framework is detected) |
Workflow
Step 1: Detect Project Type
Scan for project indicators to determine the appropriate organisation approach:
- Feature-heavy app (SPA, Next.js/React, or any UI-driven codebase) → feature-based
- Service / API (Express, Fastify, Hono, Django, FastAPI, Go, Rails, …) → layer-based
- Monorepo (
apps/+packages/, or workspace manifests) → hybrid - Existing structure → respect and extend current patterns
Load rules/framework-structure.md only when a framework it covers is detected (currently Next.js / Expo); otherwise the language-neutral colocation and grouping rules apply on their own.
Step 2: Audit
Check the existing structure against all rules.
Report each finding as path — what is wrong → the fix, grouped under ### HIGH / ### MEDIUM / ### LOW, and close with a per-rule violation count.
Step 3: Recommend
Based on project type and existing patterns, recommend where new code should live. Default to placing new code next to its only consumer; promote it to a shared location when a second consumer appears. Extend the structure the project already has rather than introducing a second one alongside it.
Step 4: Fix
Apply fixes for each violation:
- Create the destination directory first if it does not exist (
mkdir -p <dest>) —git mvfails when the target directory is missing - Move files to their correct location with
git mv - Update all import paths in dependent files
- Verify no broken imports remain after moves
What ships with it
5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 9d ago First seen · 57 lines · 32 tokens per session scan A 0d372acedd43
project-structure is a skill published in the GitHub repository tartinerlabs/skills (8 stars, last pushed 17d ago), licensed MIT. It adds 32 tokens to every session and 590 once invoked, about $0.0002 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
code-review
You are a senior code reviewer. You receive diffs via stdin.
mainframe
Use when Pi writes, reviews, or executes bash; use MAINFRAME tools, AWM, and guarded function execution when available.
mainframe
Discover MAINFRAME read-only shell helpers and route durable agent authority through its control plane when available.
skit
Run, inspect, and manage entries in the user's skit library — their personal hub, manager, and launcher for scripts in many languages (Python, shell, JS/TS, and more), executables, command templates, and AI-agent prompts, with typed parameter forms, saved presets, and per-entry launch policy. Use when the user asks to…
subagent-dev
Execute implementation plans using fresh subagents per task with two-stage review. Auto-triggered for plans with multiple independent tasks. Also available as /subagent-dev.
clarify
Turn vague requests into structured, testable specs through collaborative design. Auto-triggered when requirements are ambiguous. Explores intent, constraints, and alternatives before implementation. Also available as /clarify.