clarify

A workflow for continuing Cladding onboarding after a user answers a pending product question.

In plain words
What is it for?
Use it to prepare and apply an onboarding clarification, show proposed changes when review is needed, and finish only when Cladding reports completion.
Why use it?
It prevents the system from guessing answers and ensures the user's response is carried through the required review process.

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

Made for: Claude Code, Codex.

Per session 57 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 347 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 $0.00057 $0.00347
Opus 5 $0.00028 $0.00173
Sonnet 5 $0.00011 $0.00069
Haiku 4.5 $0.00006 $0.00035

Measured yesterday against content hash 5d08bbb82125, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

clarify 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/antigravity/skills/clarify/SKILL.md · 19 lines

What it actually says

Cladding clarify

Use this workflow only for an answer contained in a new user message after Cladding displayed the pending question. Never infer, synthesize, or reuse an answer from an initialization turn. If no new user answer exists, stop without calling either clarify tool.

Use this workflow only after Cladding initialization returned a pending question and the user has answered it.

  1. Call clad_prepare_clarify with the user's answer verbatim.
  2. Read the returned prompt, current state, and artifacts. Draft the structured refinement required by clad_clarify using the current host model.
  3. Call clad_clarify with the same answer, the one-time token, and the draft.
  4. Ask nextQuestion verbatim when one remains.
  5. If the result is needs_review, show the proposal diffs for every pendingReview target and wait for explicit user approval. Only then call clad_resolve_onboarding_review with the approved targets. Never describe onboarding as complete while review remains.
  6. Report completion only when the returned status is done.

Do not run clad clarify in a shell from an AI host. Do not use MCP sampling. Never answer a product question on the user's behalf. A stale, malformed, replayed, or answer-mismatched apply request is a no-op and must be prepared again.

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 · 19 lines · 57 tokens per session scan A 5d08bbb82125

Subscribe to this mod's changes

clarify is a skill published in the GitHub repository qwerfunch/cladding (14 stars, last pushed 3d ago), licensed MIT. It adds 57 tokens to every session and 347 once invoked, about $0.0003 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.

Related

Other skills, from other repositories

map-plan

ARCHITECT phase - decompose complex tasks into atomic subtasks with research, spec, and branch-scoped plan artifacts under .map.

azalio/map-framework · 31 tokens

map-review

Interactive 4-section code review using monitor, predictor, and evaluator agents plus the user and maintainer role reviewers on current changes. Use when reviewing a diff, PR, or staged work before merge. Do NOT use to plan or implement; use map-plan or map-efficient.

azalio/map-framework · 58 tokens

map-debug

Structured MAP debugging via task-decomposer, actor, and monitor agents. Use when reproducing a bug, isolating a regression, or diagnosing an error with specialized agents — including failing or flaky tests (pytest AssertionError), crashes and segmentation faults, memory-corruption or memory errors in native/C…

azalio/map-framework · 213 tokens

map-learn

Capture reusable lessons after a completed MAP workflow. Use when a MAP run has finished and you want rules written to .claude/rules/learned/ from a workflow summary or handoff. Do NOT use during active implementation.

azalio/map-framework · 51 tokens

map-efficient

State-machine MAP execution workflow for Codex. Use when implementing an approved MAP plan end to end, resuming from branch MAP taskplan or stepstate.json artifacts, or running non-trivial multi-subtask work. Use map-fast for tiny one-shot edits.

azalio/map-framework · 55 tokens

map-task

Execute a single subtask from an existing MAP plan via Actor and Monitor. Use when map-plan has decomposed work and you want fine-grained control over one subtask. Do NOT use without an existing plan; run map-plan first.

azalio/map-framework · 51 tokens