Pristine Skill

REVIEW · 70
Community indexed

First-Time Principle agent skill — no patching, no residue, single source of truth, adversarial verification, memory drift scan, source map index.

Verified installs0
Stars33
Version1.0.0
Quality73/100 · Strong
Trust70/100 · Sandbox only
Audit82/100 · Needs review

Supply asset profile

Coding and developer agents

Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.

Browse track

Scenario

Coding agents

I need a coding agent that can understand a repository, edit code, and review pull requests.

Agent fit

Claude Code + OpenAI Agents + CLI

Codex, Claude Code, Cursor, CLI, or custom agents.

Install

Ready

npx skills add newbanser/pristine-skill

Maintenance

fresh

9d since push

Risk

Needs review

Low GitHub adoption signal

GitHub quality

33

73/100 Quality · 78/100 Trust

Coverage tags

CodingCoding agentscoding-agentsskillagent

Review notes

Low GitHub adoption signal · Quality score needs review

Agent adoption scorecard

Trust, audit, and install readiness at a glance

These scores combine public repository metadata, OpenAgentSkill review signals, maintenance freshness, and install readiness. They are a shortlist signal, not a replacement for human review.

Quality

Strong
73

Solid option that is likely worth shortlisting for production workflows.

Trust

Sandbox only
70

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

Audit

Needs review
82

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

OpenAgentSkill Trust Score v5

Human review before install

Run only in a sandbox and compare close alternatives before using it for real work.

JavaScriptCodexClaude CodeCursorOpenAgentSkill CLI

Stars

33 GitHub stars

Repo activity

33 stars, 0 forks

Maintenance

9d since push

License

MIT

Install

npx skills add newbanser/pristine-skill

Install safety

standard package or runtime install path

Permission surface

shell or command execution

Agent outcomes

No agent outcome data yet

Docs

Strong README/SKILL.md context

Risk summary

Review before production

  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 33 GitHub stars
  • Stars/forks activity: 33 stars, 0 forks; issue activity unavailable in current metadata

Install readiness

Install path available

  • Install path is available
  • Repository evidence is available
  • License is declared
  • No Agent Proven outcome evidence yet

Agent-readable metadata

Machine-readable decision data for this skill.

Use this block or the embedded JSON to decide whether an agent should install this skill, choose an alternative, or ask for human review first.

Open JSON

Suited tasks

  • Coding agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects
  • Inspect source files

Suited agents

JavaScriptCodexClaude CodeCursorOpenAgentSkill CLIOpenAI AgentsCLI

Install decision

Command
npx skills add newbanser/pristine-skill
Policy
review
Human review
yes

Trust and risk

Trust
70/100
Audit
82/100
Risk level
Needs review

Outcome loop

Endpoint
/api/agent/outcome
Event ID
resolve
Outcomes
5

Install command

npx skills add newbanser/pristine-skill

Do not use when

  • teams that need a vendor-supported SLA
  • production agents without a repository review
  • Low GitHub adoption signal
  • No OpenAgentSkill engagement data yet
  • High-risk permission hints: Shell or command execution

Agent safety v2

54/100 · Avoid automatic install

Experimentalreview

Sparse or mixed signals. Useful for discovery, but not for autonomous installation.

Test manually in an isolated workspace and compare against safer alternatives.

Resolve via API

high

Shell or command execution

Skill metadata references terminal, CLI, shell, subprocess, or command execution workflows.

medium

Network access

Skill likely fetches remote pages, APIs, repositories, or external services.

medium

Filesystem access

Skill may read or write project files, documents, generated artifacts, or local workspace state.

  • High-risk permission hints: Shell or command execution
  • Low GitHub adoption signal

Install targets

Install this skill in your agent workflow

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

skill install

OpenAgentSkill CLI

Resolve policy, run the source installer safely, and report a verified install receipt.

$ npx --yes https://github.com/Leon-Drq/openagentskill/releases/download/cli-v0.2.1/openagentskill-0.2.1.tgz install newbanser-pristine-skill

Agent resolve plan

Let an agent verify fit before installing.

The Resolve API returns the selected skill, alternatives, safety policy, audit notes, install target, and copy-paste prompt an agent can follow without scraping this page.

Open text plan

Agent should check

  • Task fit and alternatives from Resolve API.
  • Audit score, trust score, and safety policy warnings.
  • Install target compatibility for Codex, Claude Code, Cursor, or CLI.

Copy prompt

Task: Use Pristine Skill in this workspace.
Resolve first: https://www.openagentskill.com/api/agent/resolve?task=Use%20Pristine%20Skill%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Review install handoff: https://www.openagentskill.com/api/skills/newbanser-pristine-skill/install
Install command: npx skills add newbanser/pristine-skill
Before running it, summarize audit warnings, required permissions, and the fallback skill if install is risky.

Agent handoff

Give an agent the install path, not another directory page.

Use the public install endpoint to fetch the command, safety checklist, target prompts, and canonical links for this skill.

Open install API

Agent prompt

Use Pristine Skill for this task. Review https://www.openagentskill.com/api/skills/newbanser-pristine-skill/install, then install with: npx skills add newbanser/pristine-skill

Registry metadata

Agent-readable profile for automatic skill selection.

This page exposes the same decision, trust, audit, use-case, and install signals through the Registry API, so agents can rank this skill without scraping the UI.

Open manifest

Agent fit

72/100

Coding agents

Platforms

JavaScript, Claude Code, OpenAI Agents

Audit report

Needs review · 82/100

A machine-readable review of install readiness, security metadata, maintenance, and adoption risk.

View audit reportView eval report

Agent decision cockpit

Companion skill for Coding agents

Shortlist this skill and compare it with close alternatives before production adoption.

72
Readiness
Shortlist
Stage

Role in stack

Companion skill

Primary fit

Coding agents

Trust label

Strong shortlist

Install path

Command ready

Use when

  • Coding agents workflows
  • Claude Code teams
  • builders willing to evaluate younger projects

Evidence

  • recent repository activity
  • install command or GitHub repo available
  • 73/100 quality profile

review first

  • Low GitHub adoption signal
  • No OpenAgentSkill engagement data yet

Implementation path

  1. 1Install it in a sandbox agent and run one Coding agents task end to end.
  2. 2Compare output quality, latency, and failure behavior against at least one alternative.
  3. 3Promote it into production only after reviewing repository permissions, license, and maintenance signals.

Trust profile

Sandbox only

Useful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.

70
OpenAgentSkill Trust Score

GitHub adoption

CHECK

33 GitHub stars

Stars/forks activity

CHECK

33 stars, 0 forks; issue activity unavailable in current metadata

Recent maintenance

PASS

9d since push

License clarity

PASS

MIT

Good signals

  • AI review approved
  • Install path is available
  • Repository evidence is available
  • Recently maintained repository
  • Install command has no obvious high-risk pattern
  • Outcome loop is ready but needs first real agent run

Review before install

  • Low GitHub adoption signal
  • Quality score needs review
  • GitHub adoption: 33 GitHub stars
  • Stars/forks activity: 33 stars, 0 forks; issue activity unavailable in current metadata
  • No real agent outcome reports yet
  • Human review required before unattended installation

Recommended action

Run only in a sandbox and compare close alternatives before using it for real work.

Quality profile

Strong candidate for agent workflows

Solid option that is likely worth shortlisting for production workflows.

73
GitHub stars
33
Freshness
9d ago
Install ready
Yes
License
MIT
Review before install: Low GitHub adoption signal

Workflow fit

Use this skill in these scenarios

Workflow fit

Add it to a complete workflow

Alternative shortlist

Compare before you install

Similar skills that may fit this task.

Compare all

Overview

# Pristine

[English](README.en.md) | **简体中文**

![Pristine cover](cover.png)

如果失忆是根因,那就让AI的每次重生都遵从纯净原则。

这或许是你唯一需要使用的agent skill,让你的产出永远像第一次写出来一样。 纯净、清晰、节约。

支持 Claude Code、OpenAI Codex、OpenCode、OpenClaw(开放 Agent Skill 格式)。

**当前版本:v1.6.0**

## 你需要知道

在 AI 辅助开发中,补丁的累积方式和纯人类团队不一样:

- 代码常被重写,但 **文档和记忆是跨会话唯一的桥** —— 一条过期的记录会让下一个 Agent 基于错误前提做决定。 - Agent 读的是整个文件,不是 diff —— 每一个遗留的特殊分支都在稀释真实设计的信号。 - 一个"能用"的补丁是最容易被复制的,因为它最不需要理解。每一轮打补丁,都在教下一个会话打补丁。

Pristine 是反向的力:每一次改动都像第一次写出来,让系统朝清晰演进,而不是朝熵演进。

## 你的AI需要知道

| 定律 | 含义 | |------|------| | **追溯根源**(No patching) | 修根因,不修症状。没有 `if` 特殊分支、没有复制改参数的逻辑、没有绕开问题的开关。补丁堆比干净重写更糟时,就重写。 | | **代码自释**(Code explains itself) | 名字承载"是什么"。注释只说"为什么":业务规则、约束、刻意的取舍。没有解释性注释、没有注释掉的代码块。 | | **不留残渣**(No residue) | 没有备份、草稿、死代码、中间状态。被取代的规则就地更新,绝不追加"截至……"的说明。 | | **部署如一**(Deployment parity) | 线上跑的就是本地审过的。没有只在线上做的快速修复 —— 仓库必须始终代表现实。 | | **单一真源**(Nothing extra) | 每个行为只有一个来源:先复用已有的,不需要存在的就不写。非平凡逻辑留一个可运行的机械验证 —— 自检是人类的习惯,不是 AI 的机制。 | | **会话成本**(Session cost) | 无限增长的会话和无限增长的文件是同一种熵。约 15 轮时,主动提议重置。 | | **上线初稿**(First draft before launch) | 上线前没有存量用户:改定义,不改兼容。没有迁移、没有 `ALTER TABLE`、没有兼容层 —— 只为了承载旧形态的代码,一律删掉。 |

## 安装

把 `SKILL.md` 复制到你的 Agent 技能目录:

```bash # Claude Code mkdir -p .claude/skills/pristine cp SKILL.md .claude/skills/pristine/

# OpenAI Codex mkdir -p .agents/skills/pristine cp SKILL.md .agents/skills/pristine/

# OpenCode mkdir -p .opencode/skills/pristine cp SKILL.md .opencode/skills/pristine/ ```

可选:会话监视(见下)需要把 `scripts/session-watch.js` 和 `SKILL.md` 放一起 —— 或者 clone 整个仓库、让 hook 指向 clone,这样 hook 路径稳定。

## 用法

技能在你开始实现、重构、修 bug 时自动激活,也在"先打个补丁再说"的冲动出现时激活。也可以按名字主动调用:

- `pristine` —— 正式名("we work in pristine mode") - `纯净原则` / `first-time` —— 别名,通过技能描述语义识别

## 会话监视(可选配套)

[`scripts/session-watch.js`](scripts/session-watch.js) 机械地执行 15 轮规则:数当前会话的真实用户轮次,超过阈值就打印提醒。把它挂成 Claude Code 的 `UserPromptSubmit` hook(每条用户消息触发;`Stop` hook 也可以):

```json "hooks": { "UserPromptSubmit": [ { "hooks": [ { "type": "command", "command": "node /path/to/scripts/session-wat

Platform compatibility

javascriptFULL

Technical details

Version
1.0.0
License
MIT
Last updated
Aug 18, 2026
Published
Aug 14, 2026

Frameworks & tools

JavaScript

Decision snapshot

Companion skill

72
Ready
Shortlist
Stage

recent repository activity

Audit

Install review

Install and adoption review

82
Needs review
Security
84/100
Maintenance
100/100
Install
92/100
Open full auditView eval report

Agent-proven evidence

Agent-proven evidence

Outcome reports after resolve, review, install, and one narrow run.

0
Proven
Needs first agent runAuto-install: review firstLast: Unknown
Success rate
Recent failure
Outcomes
0
Output quality
Failed
0
Not relevant
0
Installs
0
Risk blocked
0
Setup needed
0
Production
0

No agent outcome data yet. The first agent run can report success, setup needs, risk blocks, failure, or not-relevant through /api/agent/outcome.

Install

Add to agent workflow

Free and open source. Review the report before installing into production agents.

Growth loop

Share kit

X

Scenario-led draft for Pristine Skill, ready for a manual X post.

Curator note
Pristine Skill: A first-principles agent skill that enforces clean coding practices, no patching, and single...

33 stars

https://www.openagentskill.com/skills/newbanser-pristine-skill?ref=x
Open X draft
Optional reply with install command
Listing + install path for Pristine Skill:
https://www.openagentskill.com/skills/newbanser-pristine-skill?ref=x

Install: npx skills add newbanser/pristine-skill

Listing source

Community indexed

Claimable

This listing was indexed from public sources and is not marked official until a maintainer claim is approved.

Creator
newbanser
Indexed by
OpenAgentSkill community index

Attribution links to the public repository or creator profile. Creators can claim the listing to update ownership signals.

Claim this skill

Owner claim

Claim this skill listing

This Community indexed listing is attributed to newbanser but is not marked official yet. Claim it to add a verified owner signal and make future launch, install, and audit updates easier to trust.

Creator backlink kit

Add the evidence badges to your README

Show the canonical listing, current trust and audit signals, and real Agent-Proven evidence where developers evaluate the repository.

[![Listed on OpenAgentSkill](https://www.openagentskill.com/api/badge/newbanser-pristine-skill?metric=listed&label=Listed)](https://www.openagentskill.com/skills/newbanser-pristine-skill)
[![OpenAgentSkill Trust](https://www.openagentskill.com/api/badge/newbanser-pristine-skill?metric=trust&label=Trust)](https://www.openagentskill.com/skills/newbanser-pristine-skill)
[![OpenAgentSkill Audit](https://www.openagentskill.com/api/badge/newbanser-pristine-skill?metric=audit&label=Audit)](https://www.openagentskill.com/skills/newbanser-pristine-skill/audit)
[![Agent Proven](https://www.openagentskill.com/api/badge/newbanser-pristine-skill?metric=proven&label=Agent%20Proven)](https://www.openagentskill.com/skills/newbanser-pristine-skill)

Author

N

newbanser

@newbanser

Health signals

GitHub stars
33
Quality score
45/100
Last GitHub push
Aug 14, 2026
Framework hints
1
OpenAgentSkill views
0
Install copies
0
Outbound clicks
0

Community signal

Share whether this skill looks useful for your agent workflow. Aggregated feedback improves rankings over time.

Trust & safety

Sandbox only

70
  • GitHub adoption33 GitHub starsCHECK
  • Stars/forks activity33 stars, 0 forks; issue activity unavailable in current metadataCHECK
  • Recent maintenance9d since pushPASS
  • License clarityMITPASS
  • README/SKILL.md completenessMetadata includes enough usage and workflow contextPASS
  • Dependency/runtime riskcommand execution surfaceINFO