scan

scan is a command for coding agents from Kaddo-kdd/kaddo. It costs 7 tokens per session (821 once invoked), scanned A, original, MIT.

A command that creates a factual inventory of a software project. It detects the programming language, framework, package manager, code and test folders, migration files, contracts, and infrastructure.

In plain words
What is it for?
Use it to scan a repository, save machine-readable project details, create a human-readable inventory, and suggest the next setup step.
Why use it?
It gives an agent a repeatable picture of the project without pretending to understand its business rules or architecture.

Command

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 commands/kaddo-kdd/kaddo/scan
Clone the repo
git clone --depth 1 https://github.com/Kaddo-kdd/kaddo

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 scan

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaddo-kdd/kaddo/scan.svg)](https://agentmods.dev/commands/kaddo-kdd/kaddo/scan)
Your own site
<a href="https://agentmods.dev/commands/kaddo-kdd/kaddo/scan"><img src="https://agentmods.dev/badge/commands/kaddo-kdd/kaddo/scan.svg" alt="Measured on agentmods" height="20"></a>
Per session 7 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 821 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 $0.00007 $0.00821
Opus 5 $0.00003 $0.00411
Sonnet 5 $0.00001 $0.00164
Haiku 4.5 $0.00001 $0.00082

Measured 5d ago against content hash 401e74e41813, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

scan 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 5d 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.

apps/docs/src/content/docs/commands/scan.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kaddo scan

Detects language, framework, package manager, code dirs, migration dirs, contract files, infra and test dirs. Suggests domains for human confirmation — never assumes.

Generated artifacts

kaddo scan persists a reusable baseline of the project's technical state:

  • .kaddo/scan.json — structured, machine-readable. Used by the CLI and future context-pack commands. Always regenerated on each scan.
  • knowledge/inventory.md — human-readable inventory you can paste into an LLM chat. Overwrite is confirmed if the file already exists.

This baseline is the first input for the Knowledge Driven Development flow: the CLI prepares deterministic signals, and your LLM agents turn them into understanding.

Scan does not interpret your system. It detects signals and asks confirmation questions — it never claims to know your business capabilities or architecture.

State-aware next step

If .kaddo/config.yml exists, kaddo scan reads the project state recorded by kaddo init and prints a next step tailored to it:

  • new → define initial knowledge, create your first work item, grow the roadmap gradually.
  • pre-ai → use this baseline to create a context pack and understand the system with LLM agents.
  • legacy → use this baseline to identify risks, unknowns and safe modernization candidates.
This is a pre-AI monorepo.
Next: Use this baseline to create a context pack and understand the existing system with LLM agents.

Scan Signals (v3.48.0)

Starting with v3.48.0, kaddo scan detects actionable signals across 14 categories:

Category Examples
auth NextAuth, Supabase Auth, Clerk, Passport
payments Stripe, Mercado Pago, PayPal, Wompi
webhooks Webhook route directories
storage AWS S3, Cloudinary, Uploadthing
background_jobs BullMQ, Supabase Edge Functions, cron dirs
email Resend, SendGrid, Nodemailer
database Prisma, Drizzle, Supabase, Mongoose
migrations Migration directories detected by scan
api_routes Next.js API routes, Express routers
tests Vitest, Jest, test directories (warns if missing)
security Helmet, CORS, RLS policies
infrastructure Docker, Amplify, Vercel, GitHub Actions
external_integrations Sentry, Redis, Algolia, Firebase
environment Environment variable names from .env.example

Read the full file on GitHub · 96 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. 5d ago First seen · 96 lines · 7 tokens per session scan A 401e74e41813

Subscribe to this mod's changes

scan is a command published in the GitHub repository Kaddo-kdd/kaddo (47 stars, last pushed 1mo ago), licensed MIT. It adds 7 tokens to every session and 821 once invoked, about $0.0000 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.