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.
npx agentmods add skills/tincopper/neeko/trellis-before-devnpx skills add tincopper/neeko --skill trellis-before-devgit clone --depth 1 https://github.com/tincopper/neekoWrote 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/skills/tincopper/neeko/trellis-before-dev)<a href="https://agentmods.dev/skills/tincopper/neeko/trellis-before-dev"><img src="https://agentmods.dev/badge/skills/tincopper/neeko/trellis-before-dev.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 | $0.00070 | $0.00616 |
| Opus 5 | $0.00035 | $0.00308 |
| Sonnet 5 | $0.00014 | $0.00123 |
| Haiku 4.5 | $0.00007 | $0.00062 |
Grade A, and why
trellis-before-dev 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 4d 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.
This is a copy
97% identical to trellis-before-dev — 6 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
What it actually says
Read the relevant development guidelines before starting your task.
Execute these steps:
-
写码前预检（改码硬闸门，不可跳过）：在修改任何代码之前，先确认以下三条：
- 文档完成：当前任务的规划文档是否齐全——复杂任务需
prd.md+design.md+implement.md全部完成并经 review（简单/轻量任务无需任务文档，直接内联实现）。 - 用户确认：用户是否已明确确认「文档已完成、可以开始实现」。仅"同意创建任务"或默认沉默不算。
- 任务激活：任务状态是否为
in_progress（python3 ./.trellis/scripts/task.py current）。 任一未满足 → 停止写代码，先补完规划文档、向用户请求明确确认，再回来。即使被催促也不要提前改码。
- 文档完成：当前任务的规划文档是否齐全——复杂任务需
-
Read current task artifacts:
prd.mdfor requirements and acceptance criteriadesign.mdif present for technical designimplement.mdif present for execution order and validation plan
-
Discover packages and their spec layers:
python3 ./.trellis/scripts/get_context.py --mode packages -
Identify which specs apply to your task based on:
- Which package you're modifying (e.g.,
cli/,docs-site/) - What type of work (backend, frontend, unit-test, docs, etc.)
- Any spec/research paths referenced by the task artifacts
- Which package you're modifying (e.g.,
-
Read the spec index for each relevant module:
cat .trellis/spec/<package>/<layer>/index.mdFollow the "Pre-Development Checklist" section in the index.
-
Read the specific guideline files listed in the Pre-Development Checklist that are relevant to your task. The index is NOT the goal — it points you to the actual guideline files (e.g.,
error-handling.md,conventions.md,mock-strategies.md). Read those files to understand the coding standards and patterns. -
Always read shared guides:
cat .trellis/spec/guides/index.md -
Understand the coding standards and patterns you need to follow, then proceed with your development plan.
This step is mandatory before writing any code.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
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.
- 4d ago First seen · 47 lines · 70 tokens per session scan A 611ea728352b
trellis-before-dev is a skill published in the GitHub repository tincopper/neeko (11 stars, last pushed 3d ago), licensed Apache-2.0. It adds 70 tokens to every session and 616 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. It is 97% identical to trellis-before-dev, differing in 6 lines, and is treated as a copy.
Other skills, from other repositories
python-debugpy
Debug Python: pdb REPL + debugpy remote (DAP).
Detrix Dynamic Observability
This skill should be used when the user asks to "debug without print", "debug", "observe running code", "add metric", "inspect variables at runtime", "see what a variable is", or mentions "detrix", "agent mode", "eBPF", "logpoint", "dynamic metrics", "debugpy", "observe code". Debugger for agents.
delegate-runtime
Internal contract for grok-delegate companion (Claude Code + Codex CLI).
grokodex-x-search
Search X/Twitter via local Grok (MCP grokxsearch). Use for recent posts, public reaction, keyword or semantic X queries, or when the user asks about discussion on X. 通过 Grokodex 用本地 Grok 检索 X。.
grokodex-critique
Read-only design challenge of local git changes or a base-branch diff via MCP grokrun with profile=critique. Use when the user wants tradeoffs, alternatives, failure modes, or approach critique without edits. 只读挑战设计/方案；必须 profile=critique。Do not use for defect-only review (use grokodex-review) or implementing fixes…
grokodex-review
Read-only code review of local git changes or a base-branch diff via MCP grokrun with profile=review. Use when the user wants a review, PR/working-tree critique of defects, or findings without edits. 只读审查本地改动；必须 profile=review。Do not use for implementing fixes (use grokodex-run).