yecl-maintenance

yecl-maintenance is a command for Claude Code from yecllsl/trae-agent-skills. It costs 0 tokens per session (1,325 once invoked), scanned A, original, MIT.

A maintenance workflow for fixing bugs in an existing codebase. It follows a systematic debugging process, uses TDD (test-driven development, where a failing test is written before the fix), and checks for regressions afterward.

In plain words
What is it for?
Use it to investigate and fix reported bugs, run regression tests, manage repeated failed fix attempts, and coordinate a patch release.
Why use it?
It provides a repeatable way to find the underlying cause of a bug instead of applying guesses, while checking that the repair does not break existing behavior.

Command for Claude Code

Written for Claude Code: $ARGUMENTS substitution.

Good fit Use it to investigate and fix reported bugs, run regression tests, manage repeated failed fix attempts, and coordinate a patch release.

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

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

Your own site · 80×15
<a href="https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-maintenance"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-maintenance.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 1,325 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 $0.01325
Opus 5 $0.00000 $0.00662
Sonnet 5 $0.00000 $0.00265
Haiku 4.5 $0.00000 $0.00133

Measured 9d ago against content hash 39422d438af4, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

yecl-maintenance 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 9d 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-maintenance.md · 149 lines

How it starts

The opening of the file, as written. The whole thing — 149 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Usage

/YECL-maintenance <BUG_DESCRIPTION> [OPTIONS]

Options

  • --feature <feature_name>: Specify the feature directory (if bug relates to an existing feature)
  • --direct-fix: Skip systematic debugging phase (use only when root cause is already known)
  • --skip-regression: Skip regression testing after fix (not recommended)
  • --max-attempts <n>: Maximum fix attempts before escalating to design phase (default: 3)

Context

  • Bug report or issue description: $ARGUMENTS
  • Phase 6 (维护) of .trae/开发流程规范.md §4.6
  • Current codebase in working directory
  • Existing specs in docs/specs/{feature_name}/ if available
  • Activates systematic-debugging Skill for root cause analysis

Your Role

You are the YECL Coordinator executing Phase 6 (维护). You systematically locate root cause using the four-phase debugging methodology, fix the bug using TDD, and verify the fix with regression testing.

Primary responsibilities:

  1. Activate systematic-debugging Skill for root cause analysis
  2. Enforce TDD fix discipline (failing test first)
  3. Manage fix attempt escalation (≥3 failures → return to design)
  4. Verify fix with regression testing
  5. Coordinate patch release

Execution Flow

Step 0: Input Validation

  1. Parse options: --feature, --direct-fix, --skip-regression, --max-attempts
  2. Extract bug description from $ARGUMENTS
  3. If description is unclear, ask clarifying questions
  4. Determine affected feature_name if --feature provided
  5. Load related specs from docs/specs/{feature_name}/ if available

Step 1: Systematic Debugging (skip if --direct-fix)

Activate the systematic-debugging Skill.

Coordinator performs the four-phase root cause analysis (§4.6):

Phase 1 - 根因调查 (Investigation):

  • Read error messages and logs
  • Stably reproduce the bug
  • Check recent changes (git log / git diff)
  • Collect evidence
  • Trace data flow through the system

Phase 2 - 模式分析 (Pattern Analysis):

  • Find a working case (similar functionality that works)
  • Compare differences between working and failing cases
  • Understand dependencies and interactions

Read the full file on GitHub · 149 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. 9d ago First seen · 149 lines · 0 tokens per session scan A 39422d438af4

Subscribe to this mod's changes

yecl-maintenance 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 1,325 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.