explain

explain is a command for Claude Code from samibs/skillfoundry. It costs 0 tokens per session (4,675 once invoked), scanned A, original, MIT.

A command that reconstructs and explains what an agent did by examining activity logs, dispatch records, and Git history. It reports the actions, file changes, and reasons it can verify.

In plain words
What is it for?
Use it to explain the last action, inspect a complete trace, follow a story or session, filter by agent, or include before-and-after file differences.
Why use it?
It helps developers understand an agent's recent work when the action is unclear or its context is spread across several records.

Command for Claude Code

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/samibs/skillfoundry/explain
Clone the repo
git clone --depth 1 https://github.com/samibs/skillfoundry

Made for: Claude Code.

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/samibs/skillfoundry/explain.svg)](https://agentmods.dev/commands/samibs/skillfoundry/explain)
Your own site
<a href="https://agentmods.dev/commands/samibs/skillfoundry/explain"><img src="https://agentmods.dev/badge/commands/samibs/skillfoundry/explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 4,675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00000 $0.04675
Opus 5 $0.00000 $0.02337
Sonnet 5 $0.00000 $0.00935
Haiku 4.5 $0.00000 $0.00468

Measured yesterday against content hash 5e82d6591105, 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 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- smoke-test.sh uses curl with no auth (acceptable for health endpoint)
.claude/commands/explain.md · 528 lines

How it starts

The opening of the file, as written. The whole thing — 528 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/explain - Execution Explainer

Reconstruct, trace, and explain the last agent action in plain English. Three levels of detail: quick, verbose, and story-level. No mystery, no ambiguity -- just cold facts about what happened and why.


Usage

/explain                       Explain the last agent action (quick mode)
/explain --verbose             Full trace with file changes and decision rationale
/explain --story STORY-XXX     All actions for a story in chronological order
/explain --agent <name>        Last action by a specific agent
/explain --session <id>        All actions from a specific session
/explain --diff                Include before/after file diffs in output

Instructions

You are the Execution Explainer -- the forensic analyst of agent activity. When a developer asks "what just happened?", you reconstruct the full trace from scattered logs, dispatch state, and git history. You never speculate. If the data is incomplete, you say so.

Core Principle: Every agent action leaves traces. Find them, connect them, explain them.


PHASE 1: CONTEXT GATHERING

Where to Look

Agent activity leaves traces in multiple locations. Search all of them, in this order:

Source Path Contains
Swarm task queue .claude/swarm/task-queue.jsonl Completed and pending swarm tasks with agent assignments
Dispatch state .claude/dispatch-state.json Wave dispatch records: which agents ran, in what order, outcomes
Remediation logs logs/remediations.md Auto-fix actions taken by fixer or debugger
Escalation logs logs/escalations.md Points where agents escalated to the user or another agent
Git log git log --oneline -20 Recent commits with agent attribution in commit messages
Scratchpad .claude/scratchpad.md Agent notes, intermediate decisions, handoff context
Agent stats memory_bank/knowledge/agent-stats.jsonl Event log with durations, outcomes, error types
Memory bank memory_bank/knowledge/decisions-universal.jsonl Decisions recorded during execution
Error log memory_bank/knowledge/errors-universal.jsonl Errors encountered and how they were handled

Read the full file on GitHub · 528 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 · 528 lines · 0 tokens per session scan A 5e82d6591105

Subscribe to this mod's changes

explain is a command published in the GitHub repository samibs/skillfoundry (12 stars, last pushed yesterday), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 4,675 tokens. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.