sdd-clarify

sdd-clarify is a command for Claude Code from GregorBiswanger/featherspec. It costs 27 tokens per session (1,014 once invoked), scanned A, original, MIT.

A critical review command for a completed software specification. A specification is a written description of what should be built and how success will be checked.

In plain words
What is it for?
It is for reviewing files in a project's .specs directory, checking them against project rules, and finding unclear or incomplete requirements before implementation.
Why use it?
It looks for contradictions, vague wording, requirements that cannot be tested, hidden implementation decisions, and missing failure cases. It reports problems instead of rewriting the specification.

Command for Claude Code

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 commands/gregorbiswanger/featherspec/sdd-clarify
Clone the repo
git clone --depth 1 https://github.com/GregorBiswanger/featherspec

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.

agentmods badge for sdd-clarify

README.md
[![agentmods](https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-clarify.svg)](https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-clarify)
Your own site
<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-clarify"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-clarify.svg" alt="Measured on agentmods" height="20"></a>
Per session 27 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,014 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 $0.00027 $0.01014
Opus 5 $0.00014 $0.00507
Sonnet 5 $0.00005 $0.00203
Haiku 4.5 $0.00003 $0.00101

Measured 4d ago against content hash bb09427ac157, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

sdd-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 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.

.claude/commands/sdd-clarify.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/sdd-clarify — Adversarial Spec Review

The user may name a spec path after the command. If none is given — or the named path does not exist — list what sits under .specs/ and ask which one to review.

Read it as a stranger

If this session wrote or discussed the spec, do not review it here. Delegate to a subagent that receives only the spec path and AGENTS.md, or tell the user to run this in a fresh session — in-context knowledge cannot be unread. Only if neither is possible, fall back to role-play:

Assume no conversation history. Whatever was discussed while the spec was written is not available to you and must not be inferred — if you find yourself filling a gap from context, that gap is exactly what you are here to report. The context that produced an ambiguity is the worst placed to find it; your only advantage is that you were not there.

Read the spec, and read AGENTS.md for the constraints it must respect. Read the code the spec touches only when you need it to judge whether a claim is decidable. Do not read the plan — a plan that already resolved an ambiguity would hide it from you.

List, do not resolve

Your job is to find, not to fix. Do not rewrite the spec, do not propose wording, do not answer your own findings. A model asked to resolve ambiguity resolves it silently with whatever is statistically plausible; that is the failure this command exists to catch.

Produce exactly six lists, in DocLanguage. Quote the spec. An empty list is a real and useful answer — say "none found" rather than manufacturing an item.

1. Contradictions

Two statements that cannot both hold. Look hardest between sections that are rarely read together: a business rule against an acceptance criterion, an out-of-scope entry against a functional requirement, a non-functional limit against the main flow.

Read the full file on GitHub · 89 lines

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 · 89 lines · 27 tokens per session scan A bb09427ac157

Subscribe to this mod's changes

sdd-clarify is a command published in the GitHub repository GregorBiswanger/featherspec (45 stars, last pushed 5d ago), licensed MIT. It adds 27 tokens to every session and 1,014 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 2026-08-30.