req-capture

A guided requirements interview that records what a software project needs in a discovery document. It covers users, problems, success measures, functional needs, quality requirements, limits, and exclusions.

In plain words
What is it for?
Use it to explore a topic, answer structured questions, check related specifications, and create a document in backlog/discovery/.
Why use it?
It turns an unclear idea into written requirements and highlights conflicts with existing specifications before development starts.

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/iolairus/borderlint/req-capture
Clone the repo
git clone --depth 1 https://github.com/iolairus/borderlint

Made for: Claude Code.

Per session 15 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 313 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 $0.00015 $0.00313
Opus 5 $0.00008 $0.00156
Sonnet 5 $0.00003 $0.00063
Haiku 4.5 $0.00002 $0.00031

Measured 2d ago against content hash ca3c9f94c0a6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

req-capture 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.

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/req-capture.md · 27 lines

What it actually says

Capture requirements for the topic $ARGUMENTS through a structured interview, and write the result to backlog/discovery/<topic>.md using templates/discovery.md.

Steps

  1. If no topic was given, ask what problem or initiative we are exploring. Derive a kebab-case topic name.

    The discovery doc is written in English (the repo's only content language).

  2. Interview the user with the AskUserQuestion tool, one round at a time, covering in order:

    • Who are the stakeholders/users affected, and what is the problem today?
    • What does success look like? (measurable if possible)
    • Functional needs — what must the system let users do?
    • Non-functional needs — performance, security, compliance, availability.
    • Constraints, assumptions, and explicit non-goals.

    Ask follow-ups when an answer is vague ("fast" → "fast meaning what latency, for how many users?"). Stop when each template section has substance or the user says "enough".

  3. Read openspec/specs/ and note any existing requirements that overlap or conflict; record them under Constraints & assumptions.

  4. Write backlog/discovery/<topic>.md from templates/discovery.md. Unanswered items go to Open questions — never invent answers.

  5. Suggest the next step: /task-generate <topic>.

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 · 27 lines · 15 tokens per session scan A ca3c9f94c0a6

Subscribe to this mod's changes

req-capture is a command published in the GitHub repository iolairus/borderlint (7 stars, last pushed 9d ago), licensed MIT. It adds 15 tokens to every session and 313 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.