explain

An explanation command that investigates code or a technical question and produces a self-contained HTML explanation.

In plain words
What is it for?
Use it to explain the current conversation, a file, a code symbol, or a free-form technical question for a chosen audience.
Why use it?
It turns an unfamiliar code path, design, change, or bug into an understandable account of how it works and why.

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/shdennlin/agent-plugins/explain
Clone the repo
git clone --depth 1 https://github.com/shdennlin/agent-plugins
Per session 31 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,344 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 $0.00031 $0.01344
Opus 5 $0.00015 $0.00672
Sonnet 5 $0.00006 $0.00269
Haiku 4.5 $0.00003 $0.00134

Measured yesterday against content hash 18f2c9bb185d, 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 yesterday.

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.

plugins/digest/commands/explain.md · 125 lines

How it starts

The opening of the file, as written. The whole thing — 125 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explain Command

Turn an investigation into understanding. digest explains what changed (delta); explain explains the current state — what something is, how it works end-to-end, why it was designed this way, or where a bug comes from. Output is a self-contained HTML explainer.

Arguments

Parse the following from $ARGUMENTS:

  • [path|symbol|question] — What to explain: a file/directory path, a function/class name, or a free-form question. Omit entirely to explain the findings of the current conversation (e.g. right after a debugging session).
  • -f, --for <audience> — Tailor the explainer for an audience (free-form string, same as digest). Default: developer.
  • --help or -h — Show usage information and exit.

Instructions

Step 1: Parse Arguments

  1. help: if --help or -h is present, show usage info below and stop.
  2. audience: if -f or --for is present, the next token is the audience string, verbatim. Default: developer.
  3. target: everything else joined as-is (a question may be multiple words).

Help Output

If --help or -h is present, display this and stop:

Usage: /digest:explain [path|symbol|question] [options]

Explain code state: what it is, how it works, why it's designed this way, where a bug comes from.
Produces a self-contained HTML explainer (inline SVG diagrams, collapsible evidence).

Modes:
  (no arguments)        Explain the findings of the CURRENT conversation
                        (run right after an investigation or debugging session)
  <path>                Explain a file or module: role, flow, design history
  <symbol>              Explain a function/class: role in the whole flow
  "<question>"          Answer a free-form question, e.g. "why does retry use jitter?"

Options:
  -f, --for <audience>  Tailor for an audience (manager, non-technical, "new teammate", ...)
  -h, --help            Show this help message

Examples:
  /digest:explain                          # after debugging: visualize the finding
  /digest:explain src/auth/session.ts      # how this file works and why it exists
  /digest:explain handleRetry              # this function's role in the flow
  /digest:explain "why saga pattern here?" # design rationale via git archaeology
  /digest:explain src/ -f "new teammate"   # onboarding tour

Read the full file on GitHub · 125 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. yesterday First seen · 125 lines · 31 tokens per session scan A 18f2c9bb185d

Subscribe to this mod's changes

explain is a command published in the GitHub repository shdennlin/agent-plugins (2 stars, last pushed 7d ago), licensed MIT. It adds 31 tokens to every session and 1,344 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.