yecl-requirements

yecl-requirements is a command for Claude Code from yecllsl/trae-agent-skills. It costs 0 tokens per session (1,279 once invoked), scanned A, original, MIT.

A command workflow for turning a project description into reviewed product requirements. It scans the repository and saves the resulting specification under a feature-specific folder.

In plain words
What is it for?
Use it to create or refine requirements for a feature, optionally skip the repository scan, and organize the resulting specification files.
Why use it?
It gives feature work a documented starting point and requires approval before saving the product requirements.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to create or refine requirements for a feature, optionally skip the repository scan, and organize the resulting specification files.

Compare 6 commands from other repositories ↓
Install with agentmods
npx agentmods add commands/yecllsl/trae-agent-skills/yecl-requirements
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/yecllsl/trae-agent-skills

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 yecl-requirements

README.md
[![agentmods](https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-requirements/github.svg)](https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-requirements)
Your own site
<a href="https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-requirements"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-requirements/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 yecl-requirements

Your own site · 80×15
<a href="https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-requirements"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-requirements.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 0 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,279 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 $0.00000 $0.01279
Opus 5 $0.00000 $0.00639
Sonnet 5 $0.00000 $0.00256
Haiku 4.5 $0.00000 $0.00128

Measured 10d ago against content hash 462764912ec3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

yecl-requirements 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 10d 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.

.trae/commands/yecl-requirements.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage

/YECL-requirements <PROJECT_DESCRIPTION> [OPTIONS]

Options

  • --feature <feature_name>: Specify the feature directory (kebab-case). If omitted, extracted from description.
  • --skip-scan: Skip repository scanning (not recommended; 00-repo-scan.md must already exist)

Context

  • Requirements description: $ARGUMENTS
  • Phase 1 (需求分析) of .trae/开发流程规范.md §4.1
  • Spec outputs saved to docs/specs/{feature_name}/
  • Re-runnable: if 01-product-requirements.md already exists, treats this as a refinement run

Your Role

You are the YECL Coordinator executing Phase 1 (需求分析). You perform repository scanning and orchestrate YECL-po (PRD) to produce a quality-scored PRD with user approval.

Primary responsibilities:

  1. Validate input and generate feature_name in kebab-case (see §4.0.3)
  2. Ensure docs/specs/{feature_name}/ exists before any saves
  3. Mediate all user interactions; YECL-po does not talk to the user directly
  4. Enforce "don't save until approved" rule for PRD (see §4.0.2)
  5. Stop at approval gate and wait for explicit user confirmation
  6. Achieve PRD quality score ≥ 90 before saving

Execution Flow

Step 0: Input Validation

  1. Parse options from $ARGUMENTS: --feature, --skip-scan
  2. Extract or accept feature_name (kebab-case rules per §4.0.3)
  3. If description > 500 characters, summarize the core functionality and ask user to confirm (§4.0.4)
  4. If description is unclear, ask clarifying questions before proceeding (§4.0.4)
  5. Ensure directory docs/specs/{feature_name}/ exists
  6. If 01-product-requirements.md already exists, inform user this is a refinement run and load existing PRD as baseline

Step 1: Repository Scan (skip if --skip-scan or 00-repo-scan.md exists)

UltraThink Repository Scan — apply systematic analysis:

  1. Hypotheses: Form initial hypotheses about architecture and workflow
  2. Evidence: Collect data via files and patterns — project structure, tech stack, code patterns, documentation, CI/CD
  3. Patterns: Identify coding standards, design patterns, API endpoints, module responsibilities
  4. Synthesis: Cross-check for validation, produce concise context report
  5. Output: Save scan to docs/specs/{feature_name}/00-repo-scan.md

Read the full file on GitHub · 122 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. 10d ago First seen · 122 lines · 0 tokens per session scan A 462764912ec3

Subscribe to this mod's changes

yecl-requirements is a command published in the GitHub repository yecllsl/trae-agent-skills (2 stars, last pushed 1mo ago), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 1,279 tokens. 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.