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-pipeline)<a href="https://agentmods.dev/commands/yecllsl/trae-agent-skills/yecl-pipeline"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-pipeline/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-pipeline"><img src="https://agentmods.dev/badge/commands/yecllsl/trae-agent-skills/yecl-pipeline.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 | $0.01552 |
| Opus 5 | $0.00000 | $0.00776 |
| Sonnet 5 | $0.00000 | $0.00310 |
| Haiku 4.5 | $0.00000 | $0.00155 |
Grade A, and why
yecl-pipeline 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.
How it starts
The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Usage
/YECL-pipeline <PROJECT_DESCRIPTION> [OPTIONS]
Options
--feature <feature_name>: Specify the feature directory (kebab-case). If omitted, extracted from description.--skip-scan: Skip repository scanning in requirements phase (not recommended)--direct-dev: Skip Sprint planning in design phase--skip-tests: Skip QA testing phase--skip-e2e: Skip E2E tests (unit + integration only) in testing phase--skip-review: Skip independent code review in development phase--skip-deployment: Stop after testing, do not deploy--from <stage>: Resume pipeline from a specific stage (requirements/design/development/testing/deployment). Default:requirements.--to <stage>: Stop pipeline after a specific stage. Default:deployment.
Context
- Project to develop: $ARGUMENTS
- Composite command orchestrating the six phase commands defined in
.trae/开发流程规范.md§4 - Each phase is executed by invoking the corresponding
/YECL-<phase>command - Quality-gated workflow with user confirmation at each phase boundary
- Spec outputs saved to
docs/specs/{feature_name}/
Your Role
You are the YECL Coordinator executing the full development pipeline. You orchestrate the six phase commands in sequence, enforcing quality gates and approval boundaries between phases. You do NOT re-implement phase logic; you invoke the phase commands and manage transitions.
Primary responsibilities:
- Validate input and generate
feature_namein kebab-case (§4.0.3) - Determine start/end stages based on
--from/--to - Invoke each phase command in the correct order
- Enforce quality gates between phases (§6)
- Stop at each approval boundary and wait for explicit user confirmation
- Handle phase failures and recommend remediation (return to prior phase)
- Track overall pipeline progress and report completion
Execution Flow
Step 0: Input Validation & Pipeline Planning
- Parse all options from
$ARGUMENTS - Extract or accept
feature_name(kebab-case rules per §4.0.3) - If description > 500 characters, summarize and ask user to confirm (§4.0.4)
- If description is unclear, ask clarifying questions (§4.0.4)
- Ensure directory
docs/specs/{feature_name}/exists - Determine pipeline scope:
- Start stage:
--from(default:requirements) - End stage:
--to(default:deployment, unless--skip-deployment) - If
--skip-deployment, set end stage totesting
- Start stage:
- Present pipeline plan to user and wait for confirmation
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.
- 10d ago First seen · 128 lines · 0 tokens per session scan A 3c7ad39faf7a
yecl-pipeline 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 1,552 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
template
Manage issue templates for streamlined issue creation.
sync-linear
Sync current work with Linear ticket status.
add-note
Add an internal or external note to a ConnectWise PSA ticket.
fest-show
Show festival progression (in-progress tasks, roadmap, and dependency view).
dispatcher
Pick the next-best repo to work on across the portfolio — rank free repos, recommend one, claim its lease atomically, and route to the entry command.
workpm
A project-management workflow for coordinating multiple AI workers through five stages. It includes task assignment, shared activity logs, worker replacement, and final checks.