align

A requirement-alignment interview skill that asks questions before implementation so the intended behavior, scope, design, and assumptions are clear.

In plain words
What is it for?
Use it before coding when requirements are incomplete, ambiguous, or likely to affect the final result.
Why use it?
It reduces the risk of building the wrong thing because important decisions were left unstated or misunderstood.

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/dkstm95/hope/align
Any agent
npx skills add dkstm95/hope --skill align
Clone the repo
git clone --depth 1 https://github.com/dkstm95/hope

Made for: Claude Code, Codex.

Per session 25 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 940 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 $0.00025 $0.00940
Opus 5 $0.00013 $0.00470
Sonnet 5 $0.00005 $0.00188
Haiku 4.5 $0.00003 $0.00094

Measured 2d ago against content hash 45f73b749a65, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (scripts/artifact.mjs, scripts/cli.mjs, scripts/design/tokens.mjs, …), 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.

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/hope/skills/align/SKILL.md · 120 lines

How it starts

The opening of the file, as written. The whole thing — 120 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hope Align

Inspect the task and interview the person until every material intent decision is explicit and shared. Align does not implement the task.

Do not start or manage a host goal, implementation loop, retry state, progress, or completion evidence.

Read ../write/references/writing-standard.md before drafting user-facing language. Apply it without changing the agreement, evidence distinctions, confirmation conditions, or artifact contract.

Inspect the task

Read available repository, document, and conversation evidence before asking a question. Facts belong to the evidence; intent decisions belong to the person. Do not ask the person to repeat a fact that the evidence can answer.

Keep facts, user decisions, AI proposals, assumptions, material questions, and research or implementation uncertainty distinct.

Test whether the requested work is likely to achieve the goal. Surface only an omission, contradiction, risk, unsupported assumption, edge case, or materially simpler path that could change the intended result or prevent material harm. For each concern, explain the issue, impact, evidence, and uncertainty. Do not invent concerns, treat taste as a defect, or widen the task because another product could be better.

If the person supplies an Align artifact path, read references/artifact.md and inspect it as evidence. Do not search for a repository-wide latest artifact.

Work the intent tree

Map the task as an intent tree. A branch is material when different answers could change any of these:

  • the observable outcome;
  • deliberately excluded work;
  • a person-visible or domain-visible flow;
  • who can judge the result; or
  • the risk of material harm.

The frontier is every unresolved material decision whose prerequisites are settled. Ask the whole frontier in one round. Number the questions, explain why each answer matters, and offer realistic options with a recommended default when one is sensible. Do not ask a dependent question in the same round as its prerequisite.

Read the full file on GitHub · 120 lines

Files

What ships with it

9 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. 2d ago First seen · 120 lines · 25 tokens per session scan A 45f73b749a65

Subscribe to this mod's changes

align is a skill published in the GitHub repository dkstm95/hope (8 stars, last pushed 3d ago), licensed MIT. It adds 25 tokens to every session and 940 once invoked, about $0.0001 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.