hint-mode

hint-mode is a skill for Claude Code, Codex from mindspore-ai/akg. It costs 33 tokens per session (1,269 once invoked), scanned A, original, Apache-2.0.

A guide for describing tunable parameters in a standard hint format. It turns value lists, numeric ranges, fixed values, and powers of two into configuration entries for later automatic tuning.

In plain words
What is it for?
Use it to extract parameter limits from task descriptions and create tuning configurations for values such as batch sizes, dimensions, and block sizes.
Why use it?
It removes the need to manually translate task requirements into parameter-space settings. It also helps ensure all parameter hints, including commented ones and alternate formats, are captured.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Good fit Use it to extract parameter limits from task descriptions and create tuning configurations for values such as batch sizes, dimensions, and block sizes.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/mindspore-ai/akg/hint-mode
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.

Any agent
npx skills add mindspore-ai/akg --skill hint-mode
Clone the repo
git clone --depth 1 https://github.com/mindspore-ai/akg

Made for: Claude Code, Codex.

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 hint-mode

README.md
[![agentmods](https://agentmods.dev/badge/skills/mindspore-ai/akg/hint-mode/github.svg)](https://agentmods.dev/skills/mindspore-ai/akg/hint-mode)
Your own site
<a href="https://agentmods.dev/skills/mindspore-ai/akg/hint-mode"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/hint-mode/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 hint-mode

Your own site · 80×15
<a href="https://agentmods.dev/skills/mindspore-ai/akg/hint-mode"><img src="https://agentmods.dev/badge/skills/mindspore-ai/akg/hint-mode.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,269 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. Third-party audits
  • NVIDIA SkillSpector pass 7 Sept 2026
How audits are shown
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 $0.00033 $0.01269
Opus 5 $0.00016 $0.00634
Sonnet 5 $0.00007 $0.00254
Haiku 4.5 $0.00003 $0.00127

Measured 9d ago against content hash 79f9b5a11625, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

hint-mode 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.

akg_agents/python/akg_agents/op/resources/skills/designer/hint-mode/SKILL.md · 122 lines

How it starts

The opening of the file, as written. The whole thing — 122 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Hint 模式:参数空间配置指南

概述

Hint 模式用于从任务描述中识别参数范围约束,生成参数空间配置(space_config),支持后续的自动调优。

Hint 语法格式

标准格式

# @hint: param in [val1, val2, ...]         → type='choice', values=[...]
# @hint: param in range(min, max, step=N)   → type='range', min=..., max=..., step=...
# @hint: param = value                      → type='fixed', value=...
# @hint: param in pow2(min_pow, max_pow)    → type='power_of_2', min_pow=..., max_pow=...
# @hint: param in pow of 2                  → type='power_of_2'

兼容格式

# @range_hint("param", start=min, end=max)  → type='range', min=..., max=...
# @elemwise_hint("param", [val1, val2])     → type='choice', values=[...]
# @elem_hint("param", [val1, val2])         → type='choice', values=[...]

示例

# @hint: batch_size in pow of 2             → {'type': 'power_of_2', 'min_pow': 3, 'max_pow': 6}  # [8, 16, 32, 64]
# @hint: dim in range(16, 65536)            → {'type': 'range', 'min': 16, 'max': 65536, 'step': 1}
# @hint: BLOCK_M in [64, 128, 256]          → {'type': 'choice', 'values': [64, 128, 256]}

Hint 提取规则

  1. 识别所有 hint:包括被注释掉的 hint(# @range_hint),都应识别并提取
  2. 完整提取:如果有多个 hint,必须全部提取,不能遗漏
  3. 格式转换
    • 装饰器格式(如 @range_hint("param", st=8, ed=64))→ 提取括号内信息
    • 注释格式(如 # @hint: param in range(16, 65536))→ 提取冒号后声明
    • 统一转换为标准的 SPACE_CONFIG 字典格式

参数空间配置模板

"""参数空间配置"""
import torch  # 或 import mindspore as ms

# ===== 参数空间定义 =====
SPACE_CONFIG = {
    'param1': {'type': 'choice', 'values': [val1, val2, ...]},
    'param2': {'type': 'range', 'min': min_val, 'max': max_val, 'step': step_val},
    'param3': {'type': 'power_of_2', 'min_pow': min_exp, 'max_pow': max_exp},
    # ... 根据 hint 提取的所有参数
}

# ===== 元信息 =====
META_INFO = {
    'op_name': 'op_name',
    'framework': 'torch',  # 或 'mindspore'
    'param_names': ['param1', 'param2', ...]  # 参数名列表,保持顺序!
}

# ===== 输入构造函数 =====
def create_inputs(param1, param2, ...):
    """
    根据参数生成输入
    参数顺序必须与 META_INFO['param_names'] 一致
    """
    ...
    return [tensor1, tensor2, ...]

# ===== 初始化输入函数(可选)=====
def get_init_inputs():
    """如果原始代码有此函数,完整复制"""
    return []  # 或 ["auto"]

Read the full file on GitHub · 122 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 · 122 lines · 33 tokens per session scan A 79f9b5a11625

Subscribe to this mod's changes

hint-mode is a skill published in the GitHub repository mindspore-ai/akg (259 stars, last pushed 29d ago), licensed Apache-2.0. It adds 33 tokens to every session and 1,269 once invoked, about $0.0002 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.