explain

explain is a command for coding agents from Kaddo-kdd/kaddo. It costs 20 tokens per session (2,226 once invoked), scanned A, original, MIT.

A command that summarizes what Kaddo knows about the current project and what is still missing. Kaddo is a project-knowledge tool that stores information about code, work, ownership, and plans.

In plain words
What is it for?
Use it for onboarding, handoffs, checking knowledge coverage, reviewing work-item states, examining a specific area or artifact type, and finding missing project information.
Why use it?
It gives people and AI assistants a quick, repeatable project status view without requiring an AI model. It also points to suggested next steps.

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/explain
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 explain

README.md
[![agentmods](https://agentmods.dev/badge/commands/kaddo-kdd/kaddo/explain.svg)](https://agentmods.dev/commands/kaddo-kdd/kaddo/explain)
Your own site
<a href="https://agentmods.dev/commands/kaddo-kdd/kaddo/explain"><img src="https://agentmods.dev/badge/commands/kaddo-kdd/kaddo/explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 20 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,226 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 $0.00020 $0.02226
Opus 5 $0.00010 $0.01113
Sonnet 5 $0.00004 $0.00445
Haiku 4.5 $0.00002 $0.00223

Measured 4d ago against content hash 324db06978c5, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

explain 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.

apps/docs/src/content/docs/commands/explain.md · 198 lines

How it starts

The opening of the file, as written. The whole thing — 198 lines — stays where its author put it; the contents beside it link to each section on GitHub.

kaddo explain                      # project explanation (human-readable)
kaddo explain --for human          # same, explicit
kaddo explain --for agent          # compact structured JSON
kaddo explain --scope payments     # focused: limit to a domain or keyword
kaddo explain --type adr           # focused: limit to one artifact type
kaddo explain --since 2026-01-01   # focused: limit by creation date

Project explanation (no filters)

Run without filters, kaddo explain summarizes the current state of the project from existing Kaddo artifacts:

  • Project metadata (name, state, team, structure)
  • Detected stack (from .kaddo/scan.json)
  • Knowledge status (inventory, context pack, capabilities, architecture baseline, roadmap, agents)
  • Work Items counted by lifecycle state (draft, ready, in-progress, blocked, completed, archived)
  • Ownership coverage (how many work items declare code: globs)
  • Missing knowledge and suggested next steps

It also writes .kaddo/explain.md and .kaddo/explain.json so the explanation can be reused for onboarding, handoff or by agents. No LLM is called — the output is fully deterministic.

# Project Explanation

## Project
- Name: dotear-web
- State: pre-ai
- Team: indie
- Structure: monorepo

## Detected Stack
- Language: TypeScript
- Framework: Next.js

## Knowledge Status
- Capabilities: missing
- Roadmap: available
- Roadmap candidates: 21
- Materialized work items: 5
- Remaining candidates: 16
- Ownership coverage: 1/2 work items

## Suggested Next Steps
1. Use capability-agent to create knowledge/product/capabilities.md.
2. Materialize 16 roadmap candidate(s) with `kaddo create --from roadmap`.
3. Run `kaddo owners suggest` for Work Items without code ownership.

explain also reports the Work Items by Type distribution (Features / Bugfixes / Hotfixes / Spikes / Chores), so technical and maintenance work (chore) stays visible and distinct from delivered features:

## Work Items by Type
- Features: 12
- Chores: 4
- Spikes: 2
- Bugfixes: 1

explain also flags possible duplicate Work Items (non-blocking) — items sharing the same roadmap source candidate or the same normalized title (which catches translated duplicates like Initialize TypeScript CLI project / Inicializar proyecto TypeScript CLI). Review them before continuing.

When a roadmap is present, explain distinguishes roadmap candidates (entries the roadmap-agent proposed) from materialized Work Items (created under knowledge/delivery/work-items/). The remaining candidates count is the gap between them, and explain suggests materializing them with kaddo create --from roadmap. Candidates are read from any supported roadmap format (table, bullet, checklist, mixed initiatives, or the strict Kaddo Roadmap Agent format).

explain also groups Work Items virtually by initiative front matter. Phase and initiative remain metadata for planning and functional traceability; folders represent lifecycle state only.

Read the full file on GitHub · 198 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. 4d ago First seen · 198 lines · 20 tokens per session scan A 324db06978c5

Subscribe to this mod's changes

explain is a command published in the GitHub repository Kaddo-kdd/kaddo (47 stars, last pushed 1mo ago), licensed MIT. It adds 20 tokens to every session and 2,226 once invoked, about $0.0001 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.