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/yecllsl/trae-agent-skillsWrote 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/yecllsl/trae-agent-skills/yecl-development)<a href="https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-development"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-development.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 5.1 | $0.00000 | $0.01306 |
| Opus 5 | $0.00000 | $0.00653 |
| Sonnet 5 | $0.00000 | $0.00261 |
| Haiku 4.5 | $0.00000 | $0.00131 |
Grade A, and why
yecl-development 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 6d 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 — 130 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/YECL-development [OPTIONS]
Options
--feature <feature_name>: Specify the feature directory (required if not inferable from context)--skip-review: Skip independent code review (not recommended)--max-iterations <n>: Maximum review iterations before escalation (default: 3)
Context
- Phase 3 (开发) of
.trae/开发流程规范.md§4.3 - Prerequisites:
01-product-requirements.md+02-system-architecture.md(+03-sprint-plan.mdif not--direct-dev) - Orchestrator mediation: YECL-dev and YECL-review communicate through Coordinator
- Output: source code + unit tests +
04-dev-reviewed.md - Includes Code Review as an explicit sub-stage (§4.3 代码审查子阶段)
Your Role
You are the YECL Coordinator executing Phase 3 (开发). You orchestrate YECL-dev (TDD implementation) and YECL-review (independent code review) to produce production-ready code that passes review.
Primary responsibilities:
- Verify design prerequisites exist
- Mediate between Dev and Review during iteration loops
- Enforce TDD discipline (RED → GREEN → REFACTOR)
- Manage review iteration escalation per §4.3
- Verify dev outputs (tests pass, lint clean, security scan)
Execution Flow
Step 0: Input Validation
- Parse options:
--feature,--skip-review,--max-iterations - Determine
feature_namefrom--featureoption or context - Verify prerequisites exist:
docs/specs/{feature_name}/01-product-requirements.md(required)docs/specs/{feature_name}/02-system-architecture.md(required)docs/specs/{feature_name}/03-sprint-plan.md(required unless architecture indicates direct-dev)- If missing, report error and recommend running
/YECL-requirementsand/YECL-designfirst
Step 1: Environment Isolation (门控1: 实现前)
- Verify worktree exists (activate
using-git-worktreesSkill if needed) - If no worktree, create one before development begins
Step 2: TDD Implementation (via YECL-dev)
Use Task tool with YECL-dev agent:
Repository Context: [00-repo-scan.md content or path]
Feature Name: {feature_name}
Working Directory: {project_root}
Task: Implement ALL features across ALL sprints according to specifications
Instructions:
1. Read PRD from docs/specs/{feature_name}/01-product-requirements.md
2. Read Architecture from docs/specs/{feature_name}/02-system-architecture.md
3. Read Sprint Plan from docs/specs/{feature_name}/03-sprint-plan.md
4. Identify and implement ALL sprints sequentially (Sprint 1, Sprint 2, etc.)
5. Complete ALL tasks across ALL sprints before finishing
6. TDD discipline: RED (failing test) → GREEN (minimal impl) → REFACTOR
7. Create production-ready code with tests for the entire feature set
8. Report implementation status for each sprint and overall completion
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.
- 6d ago First seen · 130 lines · 0 tokens per session scan A f2e9616ec98f
yecl-development 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 1,306 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.
Other commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
dashboard
Generar dashboard HTML local con métricas de eficiencia del proyecto SDD.
usage-add
PitWay: Accumulate measured planning or qa token usage onto a milestone.
hub-tdd
TDD workflow for MCP Hub implementation. Types → Tests (red) → Implementation (green) with git gates.
eval
Evaluate and improve one healthcare agent's system prompt. Run up to 5 iterations of: prepare fixed questions -> answer -> judge -> improve -> re-score -> commit if better.
tdd
A command that follows test-driven development (TDD), a method where you write tests before the code they check. It moves through writing a failing test, adding the smallest implementation, and then improving the code.