A command that asks a fixed number of clarifying questions before work begins. It offers lettered answer choices and then waits for the user's response.

Use it when a task needs deliberate clarification first, with between one and ten questions.

It reduces the chance of starting with unclear requirements or making the wrong assumptions about a request.

align — Skill for Claude Code by mishahanin/heading-os

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.

Any agent

npx skills add mishahanin/heading-os --skill align

Clone the repo

git clone --depth 1 https://github.com/mishahanin/heading-os

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.

README.md

[![agentmods](https://agentmods.dev/badge/skills/mishahanin/heading-os/align/github.svg)](https://agentmods.dev/skills/mishahanin/heading-os/align)

Your own site

<a href="https://agentmods.dev/skills/mishahanin/heading-os/align"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/align/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/skills/mishahanin/heading-os/align"><img src="https://agentmods.dev/badge/skills/mishahanin/heading-os/align.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 82 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.

When invoked 2,530 The whole file, excluding the scripts and references it only reads on demand.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe. Third-party audits

NVIDIA SkillSpector warn 7 Sept 2026

SkillSpector: 1 finding, up to medium

These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →

medium Excessive Agency · line 12
Skill selects an external model or provider that may use a different account or billing plan than the operator expects. Undisclosed model switches can cause unexpected cost or quota consumption.

Fix: Remove the model/provider override or disclose it prominently and require explicit operator approval before invoking an external coding CLI or billed model.

How audits are shown

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.

Model	Per session	Once invoked
Fable 5.1	$0.00082	$0.02530
Opus 5.5	$0.00033	$0.01012
Sonnet 5.5	$0.00016	$0.00506
Haiku 4.5	$0.00008	$0.00253

Measured 1mo ago against content hash 38f2b1500cf1, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

align 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 1mo 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.

.claude/skills/align/SKILL.md · 268 lines

How it starts

The opening of the file, as written. The whole thing — 268 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/align - Force N numbered clarifying questions before doing any work

Manual escalation lever above the default prompt-refinement.md rule. When the user invokes /align N they are explicitly summoning a clarification gate with exactly N numbered + lettered questions, each carrying a single committed recommendation. Single-shot per invocation - after Phase 3 approval the skill exits and normal posture resumes.

Design spec: build/spec/docs/superpowers/specs/2026-05-13-align-skill-design.md (data overlay: under .heading-os-data/build/spec/).

Phase 1 - Pre-flight + target identification

Three sub-steps, all silent on success.

1.1 Parse and validate N

Read $ARGUMENTS:

Empty -> N = 5 (default)
Integer string "1" through "10" -> N = int(arg)
Anything else ("0", "100", "abc", "5.5", "-3") -> abort with the single-line error and stop. The error is the entire output:
```
/align expects N between 1 and 10. Got: {arg}. Try `/align 5`.
```

1.2 Detect CEO vs exec context

One Glob call to set the recommendation label:

Glob("canon/reference/reference/misha-voice.md")

Match found -> voice_mode = "ceo", label = Моя рекомендация. Bilingual EN/RU per the user's preceding message language.
No match -> voice_mode = "exec", label = My recommendation. English-only.

The voice_mode flag controls only the label string, not the conversation language. Conversation language always matches the user's last message.

1.3 Identify the substantive target request

Walk back through conversation context (in-LLM, no tool call) to find the latest substantive user turn preceding the /align invocation. Rules:

Skip the /align invocation itself.
Skip bare command words (ok, yes, approved, go, proceed, thanks).
Skip prior /align answer lines that look like 1a, 2c, 3 - custom: ....
Accept the first prior user turn containing an actionable request - typically the longest recent turn, often with a question, instruction verb, or pasted context.

Read the full file on GitHub · 268 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.

1mo ago Changed 38f2b1500cf1
1mo ago Changed · +1 lines ec5ca901df1d
1mo ago First seen · 267 lines · 82 tokens per session scan A f4cc438a8acc

Subscribe to this mod's changes

align is a skill published in the GitHub repository mishahanin/heading-os (11 stars, last pushed 1mo ago), licensed Apache-2.0. It adds 82 tokens to every session and 2,530 once invoked, about $0.0003 per session on Opus 5.5. 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.

Claude Code LLM Security ai-agent anthropic automation

align

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

/align - Force N numbered clarifying questions before doing any work

Phase 1 - Pre-flight + target identification

1.1 Parse and validate N

1.2 Detect CEO vs exec context

1.3 Identify the substantive target request

What ships with it

What this file has done since we first saw it

Other skills, from other repositories

dcf-model

ascii-video

grounded-citations

hermes-agent-skill-authoring

systematic-debugging

baoyu-article-illustrator