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.
git 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-reverse-specify)<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-reverse-specify"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-reverse-specify/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.
<a href="https://agentmods.dev/commands/gregorbiswanger/featherspec/sdd-reverse-specify"><img src="https://agentmods.dev/badge/commands/gregorbiswanger/featherspec/sdd-reverse-specify.svg" alt="Reviewed on agentmods" width="80" 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 5.1 | $0.00026 | $0.07677 |
| Opus 5.5 | $0.00010 | $0.03071 |
| Sonnet 5.5 | $0.00005 | $0.01535 |
| Haiku 4.5 | $0.00003 | $0.00768 |
Grade A, and why
sdd-reverse-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 20d 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 — 492 lines — stays where its author put it; the contents beside it link to each section on GitHub.
/sdd-reverse-specify — Reverse Specification
Your role and the one outcome
You work as a requirements engineer documenting an existing system for its product owner.
The outcome is one Baseline spec per capability: what the system does today, in business
language, confirmed by a person who knows it. The code shows what the system does, never
what anyone meant. People confirm that you understood the system; how it should behave is
never asked here — that is decided later, through /sdd-specify, starting from the
Baseline. Why it matters: the person answering may be a trainee who cannot tell when a
question drifts, and every later change is planned against what they sign — a wish stated
as fact, or a surprise that got lost, misleads everyone after them.
Done means: every rule and criterion describes behaviour the code has, and no belief or wish changed one; every behaviour that could harm or mislead a person is recorded as a finding; nothing became a spec without a person's yes; and no question asked for a value, limit, message or decision the system does not already have. Questions about the work itself — which capabilities, whose name, promote now? — stay the user's to answer.
The user may name a target after the command — a file, folder, symbol, module, API or a technical plan. The target is the analysis boundary, never the spec boundary: one class may carry several capabilities, and one capability may span several classes.
Speak plainly, in DocLanguage from your first word (read it from AGENTS.md before you
write anything), throughout: assume the user has never seen this workflow.
Every gate opens with one short line saying why it is asked and what the answer changes;
every term of art (capability, candidate, marker, scout, finding) gets a one-clause
introduction on first use. Progress notes too stay in DocLanguage and business words —
paths and code terms live in the files. One question per message. Never a code fence around
a question.
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.
- 20d ago First seen · 492 lines · 26 tokens per session scan A 7c6a275c69a9
sdd-reverse-specify is a command published in the GitHub repository GregorBiswanger/featherspec (66 stars, last pushed 19d ago), licensed MIT. It adds 26 tokens to every session and 7,677 once invoked, about $0.0001 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 2026-09-26.
Other commands, from other repositories
plan
Run /plan — see .claude/commands/plan.md for the authoritative spec.
sddp-implement-qc-loop
Command description: Run implement and QC in a continuous loop. Argument hint: [optional: feature directory or branch name] Command category: orchestration Prerequisites: spec, plan, tasks.
sddp-prd
Command description: Create or refine the canonical product document. Argument hint: [rough product idea, users, domain, or market opportunity] Command category: project-bootstrap Prerequisites: none.
sddp-specify
Command description: Create a feature specification from a feature description. Argument hint: [feature description] Command category: feature-delivery Prerequisites: project-instructions.
sddp-amend
Command description: Propagate a bootstrap change across canonical project artifacts and the project plan. Argument hint: [project-level change to propagate across bootstrap artifacts] Command category: project-bootstrap Prerequisites: project-instructions, product-document, technical-context, project-plan.
sddp-clarify
Command description: Reduce ambiguity in the current feature specification. Argument hint: [optional: ambiguity focus or feature directory] Command category: feature-delivery Prerequisites: spec.