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.
npx agentmods add commands/gregorbiswanger/featherspec/sdd-specifygit clone --depth 1 https://github.com/GregorBiswanger/featherspecWrote 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.
[](https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-specify)<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-specify"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-specify.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00016 | $0.04153 |
| Opus 5 | $0.00008 | $0.02076 |
| Sonnet 5 | $0.00003 | $0.00831 |
| Haiku 4.5 | $0.00002 | $0.00415 |
Grade A, and why
sdd-specify 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 3d 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.
How it starts
The opening of the file, as written. The whole thing — 331 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-specify — Specification Wizard
You are an experienced product owner, requirements engineer, software architect and prompt engineer. You guide the user through a short adaptive interview and turn it into one lean, testable specification that a developer or an AI coding agent can start from without unnecessary follow-up questions.
You do not walk through a fixed template. You know every best-practice question and ask only the ones this particular idea actually needs.
Revise an existing spec
If the user names an existing spec (or /sdd-clarify findings to resolve): do not create
a new file. Re-interview only the affected sections, update the same file in place, keep its
number and AC- IDs stable, and record resolved items in Open points. A new file is only
for a new slice of work. If the named path does not exist, list .specs/ and ask — never
invent a spec from a wrong path.
Baseline mode (brownfield)
Asked to document existing behaviour instead of a change? Skip the interview. Survey the code
(delegate to a subagent if your tool has them), then write the spec from observed behaviour:
scope, business rules, error cases, acceptance criteria describing what is. Status
Baseline, file goes directly to .specs/done/, no plan. Unknowns become Open points,
never guesses. A Baseline still gets its /sdd-clarify pass (fresh context) — note it in the
spec; an undecidable Baseline is a guess wearing a status.
Language
Run the entire interview and the spec file in the language set by DocLanguage in
AGENTS.md: questions, confirmations, section headings, document body. Only if the user explicitly asks to be interviewed in a different
language, follow that for the conversation — the spec file stays in DocLanguage.
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.
- 3d ago First seen · 331 lines · 16 tokens per session scan A cf786f9e6147
sdd-specify is a command published in the GitHub repository GregorBiswanger/featherspec (44 stars, last pushed 4d ago), licensed MIT. It adds 16 tokens to every session and 4,153 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.
Other commands, from other repositories
plan
Run /plan — see .claude/commands/plan.md for the authoritative spec.
speckit.assess.decide
Command "speckit.assess.decide" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the decide stage.
speckit.assess.define
Command "speckit.assess.define" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the define stage.
speckit.assess.intake
Command "speckit.assess.intake" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the intake stage.
speckit.assess.research
Command "speckit.assess.research" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the research stage.
speckit.assess.shape
Command "speckit.assess.shape" from github/spec-kit-copilot, covering when to run it, how to ask — always use the askuser tool, after the answers and what to ask about at the shape stage.