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-maintenance)<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.
<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>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 | $0.01325 |
| Opus 5 | $0.00000 | $0.00662 |
| Sonnet 5 | $0.00000 | $0.00265 |
| Haiku 4.5 | $0.00000 | $0.00133 |
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.
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-debuggingSkill 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:
- Activate systematic-debugging Skill for root cause analysis
- Enforce TDD fix discipline (failing test first)
- Manage fix attempt escalation (≥3 failures → return to design)
- Verify fix with regression testing
- Coordinate patch release
Execution Flow
Step 0: Input Validation
- Parse options:
--feature,--direct-fix,--skip-regression,--max-attempts - Extract bug description from
$ARGUMENTS - If description is unclear, ask clarifying questions
- Determine affected
feature_nameif--featureprovided - 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
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.
- 9d ago First seen · 149 lines · 0 tokens per session scan A 39422d438af4
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.
Other commands, from other repositories
bugfix
Bug fix workflow: root cause analysis → user review → regression test + fix via TDD.
fix
Correction automatisee des bugs identifies par la QA Recette.
tdd
Correction de Bug en Mode TDD/BDD.
hatch3r-bug-pipeline
Run a known-cause bug fix through a 3-phase test-first pipeline -- reproduce + root-cause, regression-test + fix together, then root-cause-depth review -- with full sub-agent delegation.
bugfix
Regression-test-first bug fixing workflow with smart SpecSwarm/SpecTest integration.
qa
Validate an application against a Gherkin user story by spawning a QA team that drives the running app.