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 instructions/363045841/klinechartquant/agents-mdgit clone --depth 1 https://github.com/363045841/KLineChartQuantWhat 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 | $0.04362 | $0.04362 |
| Opus 5 | $0.02181 | $0.02181 |
| Sonnet 5 | $0.00872 | $0.00872 |
| Haiku 4.5 | $0.00436 | $0.00436 |
Grade A, and why
KLineChartQuant AGENTS.md 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 2d 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 — 262 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Trellis Instructions
These instructions are for AI assistants working in this project.
This project is managed by Trellis. The working knowledge you need lives under .trellis/:
.trellis/workflow.md- development phases, when to create tasks, skill routing.trellis/spec/- package- and layer-scoped coding guidelines (read before writing code in a given layer).trellis/workspace/- per-developer journals and session traces.trellis/tasks/- active and archived tasks (PRDs, research, jsonl context)
If a Trellis command is available on your platform (e.g. /trellis:finish-work, /trellis:continue), prefer it over manual steps. Not every platform exposes every command.
If you're using Codex or another agent-capable tool, additional project-scoped helpers may live in:
.agents/skills/- reusable Trellis skills.codex/agents/- optional custom subagents
Managed by Trellis. Edits outside this block are preserved; edits inside may be overwritten by a future trellis update.
KLineChartQuant — Agent Guide
代码要求
重中之重:拒绝一切治标不治本的“最小修复”，拒绝架构债，代码可读性强，可维护，不炫技。禁止硬编码字符串。 不要复杂化问题，特别是架构上。
PR 作者要求
- 不许在 PR 中使用 /goal 命令
- 不许一下子写一堆代码，中间不经过 E2E 测试、视觉回归测试
- 不许长时间自己收敛相当宽泛问题而不交由作者亲自测试
- 不许在小问题上使用严苛的校验，导致链路难以维护
- 不许未经确认就围绕一个你自己 MOCK 的数据进行开发和重构
Quick Search
- MUST USE CodeGraph MCP FIRST: You can use
codegraph_codegraph_callees, codegraph_codegraph_callers, codegraph_codegraph_explore, codegraph_codegraph_files, codegraph_codegraph_impact, codegraph_codegraph_node, codegraph_codegraph_search, codegraph_codegraph_statusto expolore project, Call analysis.It is a replacement for grep and similar commands. When you launch a sub-agent, use codegraph MCP when prompted to explore the code in the sub-agent prompt
Committing
- Must use commit-message-generator skill: When committing, always load the skill at
.opencode/skills/commit/SKILL.mdviaskill("commit-message-generator")to generate conventional commit messages. - PR descriptions should cover the entire branch: When creating a PR, describe the full scope of changes across all commits in the branch, not just the latest commit.
- You can only commit when I explicitly ask you to do it.
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.
- 2d ago First seen · 262 lines · 4,362 tokens per session scan A 5f0ab94b51de
KLineChartQuant AGENTS.md is an instructions file published in the GitHub repository 363045841/KLineChartQuant (21 stars, last pushed 2d ago), licensed MIT. It adds 4,362 tokens to every session, about $0.0218 per session on Opus 5. 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 2026-08-30.
Other instructions, from other repositories
tiny-vue AGENTS.md
Instructions for opentiny/tiny-vue, covering agents.md, 项目概述, 关键目录结构, 环境要求 and 核心命令.
heroui CLAUDE.md
Claude Code instructions for heroui-inc/heroui, covering claude.md, repository overview, key technical stack, development commands and core development commands.
tiptap tiptap.instructions.md
Instructions for ueberdosis/tiptap, covering tiptap, what is tiptap, repository layout, npm scripts and linting & formatting.
tiptap AGENTS.md
Instructions for ueberdosis/tiptap, covering tiptap, rules, before opening a pr, code style and files.
scalar AGENTS.md
Instructions for scalar/scalar, covering agents.md - ai agent guide for scalar, project overview, prerequisites, first-time setup and commands.
tiptap changeset.instructions.md
Instructions for ueberdosis/tiptap: When a user asks for a changeset to be generated, follow the following rules.