feature-requirement-gatherer

feature-requirement-gatherer is an agent for Claude Code from rp1-run/rp1. It costs 25 tokens per session (2,236 once invoked), scanned A, original, Apache-2.0.

A requirements-gathering agent that turns a high-level feature idea into business requirements and acceptance criteria. It focuses on what the product must achieve, not how developers should implement it.

In plain words
What is it for?
Use it to write or update the requirements document for a feature in a build workflow.
Why use it?
It gives a feature a clear, testable scope before technical design and coding begin. It avoids changing source code, tests, or build files.

Agent for Claude Code

Written for Claude Code: arguments in frontmatter. Also seen: model in frontmatter; positional $N argument.

Part of the rp1-dev plugin — 23 skills, 36 agents shipped together

Good fit Use it to write or update the requirements document for a feature in a build workflow.

Compare 6 agents from other repositories ↓
Install with agentmods
npx agentmods add agents/rp1-run/rp1/feature-requirement-gatherer
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.

Clone the repo
git clone --depth 1 https://github.com/rp1-run/rp1

Made for: Claude Code.

Or install rp1-dev, the plugin that ships this one along with the rest of its 23 skills, 36 agents.

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 feature-requirement-gatherer

README.md
[![agentmods](https://agentmods.dev/badge/agents/rp1-run/rp1/feature-requirement-gatherer/github.svg)](https://agentmods.dev/agents/rp1-run/rp1/feature-requirement-gatherer)
Your own site
<a href="https://agentmods.dev/agents/rp1-run/rp1/feature-requirement-gatherer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-requirement-gatherer/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.

agentmods 80×15 button for feature-requirement-gatherer

Your own site · 80×15
<a href="https://agentmods.dev/agents/rp1-run/rp1/feature-requirement-gatherer"><img src="https://agentmods.dev/badge/agents/rp1-run/rp1/feature-requirement-gatherer.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 25 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,236 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00025 $0.02236
Opus 5 $0.00013 $0.01118
Sonnet 5 $0.00005 $0.00447
Haiku 4.5 $0.00003 $0.00224

Measured 3d ago against content hash cfb2b16497a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

feature-requirement-gatherer 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.

plugins/dev/agents/feature-requirement-gatherer.md · 258 lines

How it starts

The opening of the file, as written. The whole thing — 258 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Feature Requirement Gatherer Agent

Transforms high-level reqs into detailed specs. Invoked by /build workflow.

<feature_id>$1</feature_id> $2 <phase_plan_path>{{PHASE_PLAN_PATH from prompt}}</phase_plan_path> <phase_id>{{PHASE_ID from prompt}}</phase_id> <afk_mode>$3</afk_mode> <kb_root>{{KB_ROOT from prompt}}</kb_root> <work_root>{{WORK_ROOT from prompt}}</work_root> $WORKFLOW <run_id>$RUN_ID</run_id>

Feature dir: {WORK_ROOT}/features/{FEATURE_ID}/

Constraint: WHAT not HOW. No tech impl, arch, or code. Focus on business needs. Hard Boundaries:

  • Only create or update {WORK_ROOT}/features/{FEATURE_ID}/requirements.md.
  • Do not edit source code, tests, docs outside the feature directory, or any build artifacts.
  • Do not run git commands, stage files, create commits, or claim implementation/test completion.
  • If the provided input is a bug report, audit, or research doc with proposed fixes, translate it into business requirements and acceptance criteria only.

1. KB Loading

{% include_shared "kb-progressive-loading.md" %}

Additional files:

  • {KB_ROOT}/concept_map.md - domain terminology

2. Phase Context Resolution

Resolve optional parent-phase context before PRD matching or ambiguity analysis.

2.1 Accepted Inputs

  • Explicit prompt args:
    • PHASE_PLAN_PATH
    • PHASE_ID
  • Legacy inline handoff tokens embedded inside REQUIREMENTS:
    • PHASE_PLAN_PATH=...
    • PHASE_ID=...

2.2 Resolution Rules

  1. Prefer explicit prompt args when they are non-empty.
  2. Otherwise, scan REQUIREMENTS for legacy inline tokens and strip only those tokens from the freeform requirements text before further analysis.
  3. Activate phase traceability only when both normalized values are present. If neither is present, continue normally and omit ## Planning Traceability.
  4. Accept either:
    • work-root-relative phase-plan paths such as features/{FEATURE_ID}/phase-plan.md or prds/example-phase-plan.md
    • .rp1/work/... paths; convert them to work-root-relative paths for reads while preserving .rp1/work/... display paths for output
  5. Treat any path outside {WORK_ROOT} as invalid.

Read the full file on GitHub · 258 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. 3d ago First seen · 258 lines · 25 tokens per session scan A cfb2b16497a5

Subscribe to this mod's changes

feature-requirement-gatherer is an agent published in the GitHub repository rp1-run/rp1 (38 stars, last pushed 4d ago), licensed Apache-2.0. It adds 25 tokens to every session and 2,236 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 2026-09-07.

Related

Other agents, from other repositories