explain

A research workflow for investigating a topic or problem, finding its root cause, and producing a summary with deeper analysis.

In plain words
What is it for?
It is for explaining complex issues, tracing why something happened, and deciding what action to take next. It can ask one clarifying question when the request is too vague.
Why use it?
It helps when a quick answer is not enough and prevents research from starting with an unclear question.

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

Made for: Claude Code, Codex.

Per session 32 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,805 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 $0.00032 $0.02805
Opus 5 $0.00016 $0.01403
Sonnet 5 $0.00006 $0.00561
Haiku 4.5 $0.00003 $0.00281

Measured yesterday against content hash 06c8fb8d1985, 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.

The scan reads SKILL.md. This mod also ships 1 executable file (scripts/parallel-research.sh), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

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.

- **External concepts**: use WebSearch/WebFetch. These are out of the `research-agent`'s scope — it reads this repo, not the internet. When you already know the URL, fetch it with `curl` and read the page yourself: WebFe
templates/claude/skills/explain/SKILL.md · 205 lines

How it starts

The opening of the file, as written. The whole thing — 205 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Explain — Deep Research & Root Cause Analysis

Investigate a topic until confident in root cause or core understanding. Produce an actionable executive summary plus deeper analysis.

Step graph (mirrors frontmatter steps:): step-0-validate-input → step-1-classify-complexity → step-2-frame → step-3-research → step-4-synthesize → step-5-next-action-gate

Critical

  • Validate input first. If $ARGUMENTS is empty or too vague, ask ONE clarifying question before launching research. Vague input wastes parallel-agent budget on the wrong target.
  • A class-level flaw becomes work, by default. If the explanation identifies a flaw in a shared mechanism (one affecting several files), the Step 5 AskUserQuestion default option is "Ship class fix now" per @rule:class-fix-is-atomic. Do NOT silently end at explanation — surface the chain.

step-0-validate-input

If $ARGUMENTS is empty or too vague, ask ONE clarifying question first. Do not launch research on an ambiguous target.

step-1-classify-complexity

  • Quick — well-scoped factual, single concept. Skip to Step 4 using own knowledge + one targeted lookup if needed.
  • Standard — requires tracing code/docs/external sources; single likely answer. Steps 2-4 sequentially.
  • Deep — cross-cutting, multiple possible causes, systems-level "why". Steps 2-4 with parallel research agents.

State the classification and a one-sentence restatement before proceeding.

step-2-frame

INVESTIGATION FRAME:
- Question: [precise restatement]
- Type: [concept | root-cause | failure-mode | design-rationale | comparison]
- Scope: [in scope vs out of scope]
- Hypotheses: [1-3 ranked by likelihood]
- Key unknowns: [what confirms/rejects each]

If the question references files, a project, or recent work, pull context (read files, git log). If it references a production incident, gather the same context you would to explain it — logs, the recent diff, the alert itself — but do not start fixing: this skill's job is to say WHY, and the fix is a separate decision someone should make with the explanation in hand.

Read the full file on GitHub · 205 lines

Files

What ships with it

1 file 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. yesterday First seen · 205 lines · 32 tokens per session scan A 06c8fb8d1985

Subscribe to this mod's changes

explain is a skill published in the GitHub repository Ashkaan/contextium (32 stars, last pushed 4d ago), licensed MIT. It adds 32 tokens to every session and 2,805 once invoked, about $0.0002 per session on Opus 5. 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 2026-08-30.