explain

explain is a skill for Claude Code, Codex from ohong/agent-skills. It costs 96 tokens per session (1,702 once invoked), scanned A, original, MIT.

A guided explanation skill for code changes made by an agent. It explains what changed, why, trade-offs, alternatives, risks, and possible follow-up decisions using the actual project files.

In plain words
What is it for?
Use it to walk through a code diff, explain data or user flows, compare design choices, and identify remaining risks.
Why use it?
It helps developers understand and review an agent's work instead of approving changes they cannot follow.

Skill for Claude CodeCodex

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 skills/ohong/agent-skills/explain
Any agent
npx skills add ohong/agent-skills --skill explain
Clone the repo
git clone --depth 1 https://github.com/ohong/agent-skills

Made for: Claude Code, Codex.

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/skills/ohong/agent-skills/explain.svg)](https://agentmods.dev/skills/ohong/agent-skills/explain)
Your own site
<a href="https://agentmods.dev/skills/ohong/agent-skills/explain"><img src="https://agentmods.dev/badge/skills/ohong/agent-skills/explain.svg" alt="Measured on agentmods" height="20"></a>
Per session 96 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,702 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 $0.00096 $0.01702
Opus 5 $0.00048 $0.00851
Sonnet 5 $0.00019 $0.00340
Haiku 4.5 $0.00010 $0.00170

Measured 4d ago against content hash caf663a248e6, 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.

explain/SKILL.md · 134 lines

How it starts

The opening of the file, as written. The whole thing — 134 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/explain

Help the user build enough understanding to participate in the next loop, not merely approve or reject a diff. Treat the output as a guided walkthrough of agent-made work: background first, intuition before details, code in a sensible order, and explicit checks for understanding.

Operating Principles

  • Ground every claim in the real repo state. Read the diff, surrounding code, tests, plans, PR text, commit messages, and relevant docs before explaining.
  • Preserve the user's worktree. Do not modify code, regenerate files, or clean up artifacts unless the user explicitly asks for edits.
  • Separate evidence from inference. Say "the diff shows", "the commit message says", "I infer", or "unknown" instead of inventing rationale.
  • Explain to create participation. The goal is that the user can suggest the next change, spot a weak assumption, or discuss the design fluently.
  • Prefer a literate diff over file-order narration. Group changes by concept, data flow, user flow, or decision, not alphabetically by path.
  • Use small examples, diagrams, tables, and concrete before/after behavior when they reduce mental load.

Scope Discovery

  1. Determine the change set.

    • If the user names a PR, branch, commit, range, file, or worktree, use that scope.
    • If no scope is named, inspect the current repo: git status --short, current branch, default branch, merge base, uncommitted diff, and commits ahead of the base branch.
    • In multi-worktree repos, run git worktree list before assuming the current checkout is the whole story.
    • If there is no Git repo or no clear change set, ask one concise question for the scope.
  2. Gather source material.

    • Diff/stat: git diff --stat, git diff, git diff --cached, or git diff <base>...HEAD.
    • History: git log --oneline --decorate --graph --max-count=30 and relevant git show output.
    • Project intent: README, docs, plans, ADRs, issue links, PR description, TODOs, and agent notes.
    • Verification: tests run, snapshots, build logs, lint results, CI status, manual browser checks, and any failing commands.
    • Surrounding implementation: call sites, types, tests, migrations, config, and previous patterns the change builds on or breaks.

Read the full file on GitHub · 134 lines

Files

What ships with it

2 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.

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 · 134 lines · 96 tokens per session scan A caf663a248e6

Subscribe to this mod's changes

explain is a skill published in the GitHub repository ohong/agent-skills (3 stars, last pushed 4d ago), licensed MIT. It adds 96 tokens to every session and 1,702 once invoked, about $0.0005 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.

Related

Other skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

brainstorming

You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.

obra/superpowers · 37 tokens

auto-perf-optimize

Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.

microsoft/vscode · 62 tokens

chat-perf

Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.

microsoft/vscode · 51 tokens

chat-pet-sprite-creation

Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.

microsoft/vscode · 53 tokens

cpu-profile-analysis

Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…

microsoft/vscode · 71 tokens