Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
18 changes: 11 additions & 7 deletions README.md
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
English | [简体中文](https://github.com/LE0-Lin/AgentConfigScore/blob/main/README.simplified.md) | [繁體中文](https://github.com/LE0-Lin/AgentConfigScore/blob/main/README.traditional.md)

<p align="center">
<img src="https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score.svg" alt="AgentConfigScore logo" />
<img src="https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score.svg?v=0.24.0" alt="AgentConfigScore compares baseline and candidate coding-agent instructions" width="100%" />
</p>

<p align="center"><strong>Catch known regressions in coding-agent instructions before merging.</strong></p>
Expand All @@ -23,11 +23,15 @@ reports rule-defined regressions, and uses reviewed baseline policies for CI
decisions. No model API or runtime dependencies are needed.

<p align="center">
<img src="https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif" alt="A known instruction regression is reported and blocked in CI" width="100%" />
<img src="https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif?v=0.24.0" alt="Both snapshots score 100, but moving the instruction file triggers review and exit 1" width="100%" />
</p>

[Setup demo](#quick-start) · [Workflow diagram](#what-it-helps-you-review) · [Score history demo](#score-history-demo) · [Visual gallery](https://github.com/LE0-Lin/AgentConfigScore/blob/main/docs/visual-tour.md)

The demo replays a change drawn from a merged PR. An instruction file moves to
the root with identical text. Both scans score 100, and the comparison flags
the original path for review. [Reproduce the reduced case](https://github.com/LE0-Lin/AgentConfigScore/blob/main/examples/instruction-move/README.md).

**A 100 means no active deterministic rule matched.** It does not certify
instruction usefulness, semantic correctness or safety.
[Read the score contract and limitations.](https://github.com/LE0-Lin/AgentConfigScore/blob/main/docs/limitations.md)
Expand All @@ -45,7 +49,7 @@ Existing repositories can adopt the gate without first reaching 100.
`init` enables new-error blocking and no score decrease; a passing comparison
means no regression under the selected rules and policy.

![Workflow diagram showing repository setup, PR checks against a baseline, and retained reports](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg)
![Workflow diagram showing repository setup, PR checks against a baseline, and retained reports](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg?v=0.24.0)

## Quick start

Expand All @@ -69,9 +73,9 @@ without fetching; use `agent-config-score diff origin/main` when you want an
explicit ref. The [user guide](https://github.com/LE0-Lin/AgentConfigScore/blob/main/docs/user-guide.md)
covers setup, exits and troubleshooting.

![Terminal demo showing package installation, init, and doctor](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif)
![Terminal demo showing package installation, init, and doctor](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif?v=0.24.0)

*The v0.18 demo illustrates the install, initialize, and verify steps. Use the commands above for the current setup.*
*The v0.24.0 demo shows setup and selected checks from `doctor` in a local fixture.*

## Release and source status

Expand Down Expand Up @@ -191,9 +195,9 @@ and [privacy-minimized feedback drafts](https://github.com/LE0-Lin/AgentConfigSc

## Score history demo

![Illustrative score history showing the date, score, change, and commit for each snapshot](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif)
![Recorded fixture scores fall from 100 to 82 after a risk is added, then recover to 100 when it is removed](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif?v=0.24.0)

This example shows how recorded scores and commit IDs appear together in
The chart shows three locally recorded fixture scores read by
`agent-config-score history`. [Set up the history workflow.](https://github.com/LE0-Lin/AgentConfigScore/blob/main/docs/score-history.md)

The [visual tour](https://github.com/LE0-Lin/AgentConfigScore/blob/main/docs/visual-tour.md)
Expand Down
14 changes: 8 additions & 6 deletions README.simplified.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,12 @@

在合并前发现 AI 编程助手指令中的已知退化。

![AgentConfigScore 演示](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif)
![两次扫描都是 100 分,指令文件移动触发复核,比较返回 1](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif?v=0.24.0)

[安装演示](#快速开始) · [分数历史演示](#分数历史演示) · [完整演示图集](docs/visual-tour.md)

演示基于一条已合并的 PR。指令文件原样移到仓库根目录,前后都得 100 分,比较结果仍指出需要复核的旧路径。[复跑精简案例](examples/instruction-move/README.md)。

AgentConfigScore 检查 `AGENTS.md`、`CLAUDE.md`、Cursor、Copilot、Gemini 等配置,并比较改动前后的基线,回答一个具体问题:**这次改动是否引入了已知规则能检测到的风险?**

| 改动 | 审查依据 |
Expand All @@ -17,7 +19,7 @@ AgentConfigScore 检查 `AGENTS.md`、`CLAUDE.md`、Cursor、Copilot、Gemini
| PR 放宽自己的阈值或增加豁免 | 正常比较仍使用基线策略;调用方的显式覆盖需单独审核 |
| 接受已知例外 | 必须填写原因和到期日期,并保留审计记录 |

![工作流程图,展示仓库初始化、基线回归检查与报告留存](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg)
![工作流程图,展示仓库初始化、基线回归检查与报告留存](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg?v=0.24.0)

它是确定性检查器,不是 AI 评委。**A 100 只表示没有命中生效的规则,不表示指令有用、语义完美或安全无误。** 中文文档也不意味着检测器已经能够理解任意中文指令。

Expand All @@ -37,9 +39,9 @@ agent-config-score diff

`acs` 是短命令别名。v0.23.0+ 还可以使用 `python -m agent_config_score`,避免终端 PATH 没有找到命令的问题。

![终端演示,展示安装、初始化与 doctor 检查](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif)
![终端演示,展示安装、初始化与 doctor 检查](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif?v=0.24.0)

*动图以 v0.18 为例展示接入步骤。当前版本请按上方命令安装。*
*动图使用 v0.24.0 展示本地样例的接入步骤和部分 `doctor` 检查结果。*

- [简体中文使用指南](docs/simplified/user-guide.md):安装、基线、报告、退出码与排错。
- [分数含义与限制](docs/simplified/limitations.md):先了解什么能检出、什么仍可能漏掉。
Expand Down Expand Up @@ -155,8 +157,8 @@ jobs:

## 分数历史演示

![分数历史示例,逐条显示日期、分数、变化与提交](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif)
![本地样例记录的分数从 100 降至 82,移除风险后回到 100](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif?v=0.24.0)

示例展示 `agent-config-score history` 如何把每次评分和对应提交放在一起。[历史工作流(英文)](docs/score-history.md)
图中的三次评分由 `agent-config-score history` 读取。[历史工作流(英文)](docs/score-history.md)

项目采用 [MIT 协议](LICENSE)。[发布与升级说明](docs/releases/v0.24.0.md)目前为英文。
14 changes: 8 additions & 6 deletions README.traditional.md
Original file line number Diff line number Diff line change
Expand Up @@ -4,10 +4,12 @@

在合併前發現 AI 程式開發助手指令中的已知退化。

![AgentConfigScore 示範](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif)
![兩次掃描都是 100 分,指令檔移動觸發審閱,比較回傳 1](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-demo.gif?v=0.24.0)

[安裝示範](#快速開始) · [分數歷史示範](#分數歷史示範) · [完整示範圖集](docs/visual-tour.md)

示範取材自一條已合併的 PR。指令檔原樣移至儲存庫根目錄,前後都得 100 分,比較結果仍指出需要審閱的舊路徑。[重現精簡範例](examples/instruction-move/README.md)。

AgentConfigScore 檢查 `AGENTS.md`、`CLAUDE.md`、Cursor、Copilot、Gemini 等設定,並與改動前的基準比較,回答一個具體問題:**這次改動是否引入了已知規則能偵測到的風險?**

| 改動 | 審閱依據 |
Expand All @@ -17,7 +19,7 @@ AgentConfigScore 檢查 `AGENTS.md`、`CLAUDE.md`、Cursor、Copilot、Gemini
| PR 放寬自己的門檻或增加排除設定 | 一般比較仍使用基準策略;呼叫端的明確覆寫須另行審閱 |
| 接受已知例外 | 必須填寫原因和到期日期,並保留稽核紀錄 |

![工作流程圖,展示儲存庫初始化、基準回歸檢查與報告保存](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg)
![工作流程圖,展示儲存庫初始化、基準回歸檢查與報告保存](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-workflow.svg?v=0.24.0)

它是確定性的檢查工具,不是 AI 評審。**A 100 只表示沒有命中生效的規則,不代表指令實用、語意完美或完全安全。** 提供中文文件也不表示檢查工具已經能理解任意中文指令。

Expand All @@ -37,9 +39,9 @@ agent-config-score diff

`acs` 是較短的命令別名。v0.23.0+ 也能使用 `python -m agent_config_score`,不必依賴終端機 PATH 找到主命令。

![終端機示範,展示安裝、初始化與 doctor 檢查](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif)
![終端機示範,展示安裝、初始化與 doctor 檢查](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-setup.gif?v=0.24.0)

*動畫以 v0.18 為例展示整合步驟。目前版本請依照上方命令安裝。*
*動畫使用 v0.24.0 展示本機範例的整合步驟及部分 `doctor` 檢查結果。*

- [繁體中文使用指南](docs/traditional/user-guide.md):安裝、基準、報告、結束代碼與疑難排解。
- [分數意義與限制](docs/traditional/limitations.md):先了解能偵測哪些問題,以及可能遺漏什麼。
Expand Down Expand Up @@ -155,8 +157,8 @@ jobs:

## 分數歷史示範

![分數歷史範例,逐筆顯示日期、分數、變化與提交](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif)
![本機範例記錄的分數從 100 降至 82,移除風險後回到 100](https://raw.githubusercontent.com/LE0-Lin/AgentConfigScore/main/assets/agent-config-score-history.gif?v=0.24.0)

範例展示 `agent-config-score history` 如何將每次評分與對應提交放在一起。[歷史工作流程(英文)](docs/score-history.md)
圖中的三次評分由 `agent-config-score history` 讀取。[歷史工作流程(英文)](docs/score-history.md)

專案採用 [MIT 授權](LICENSE)。[發布與升級說明](docs/releases/v0.24.0.md)目前為英文。
Binary file modified assets/agent-config-score-demo.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified assets/agent-config-score-history.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified assets/agent-config-score-setup.gif
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Binary file modified assets/agent-config-score-social-preview.png
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
84 changes: 33 additions & 51 deletions assets/agent-config-score-workflow.svg
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
Loading
Loading