Pristine Skill
First-Time Principle agent skill — no patching, no residue, single source of truth, adversarial verification, memory drift scan, source map index.
Supply asset profile
Coding and developer agents
Code review, repo analysis, testing, CI, GitHub, DevOps, and developer workflow skills.
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
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
StrongSolid option that is likely worth shortlisting for production workflows.
Trust
Sandbox onlyUseful candidate with missing or mixed trust signals. Keep it in an isolated workspace until the outcome loop proves task fit.
Audit
Needs reviewA 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.
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.
Suited tasks
- Coding agents workflows
- Claude Code teams
- builders willing to evaluate younger projects
- Inspect source files
Suited agents
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-skillDo 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
Alternative
Code Review
168.6K Stars
npx skills add mattpocock/skills --skill code-review
Alternative
Grill With Docs
164.7K Stars
npx skills add mattpocock/skills --skill grill-with-docs
Alternative
To Spec
164.7K Stars
npx skills add mattpocock/skills --skill to-spec
Alternative
To Tickets
176.7K Stars
npx skills add mattpocock/skills --skill to-tickets
Agent safety v2
54/100 · Avoid automatic install
Sparse or mixed signals. Useful for discovery, but not for autonomous installation.
Test manually in an isolated workspace and compare against safer alternatives.
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.
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-skillAgent 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 JSON
/api/agent/resolve?task=Use%20Pristine%20Skill%20for%20an%20agent%20workflow&agent=codex&max_risk=medium
Resolve text
/api/agent/resolve?task=Use%20Pristine%20Skill%20for%20an%20agent%20workflow&agent=codex&max_risk=medium&format=text
Install handoff
/api/skills/newbanser-pristine-skill/install
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.
Install handoff
/api/skills/newbanser-pristine-skill/install
LLM text format
/api/skills/newbanser-pristine-skill/install?format=text
Find alternatives
/api/skills/search?q=Pristine%20Skill&limit=3
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-skillRegistry 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.
Manifest
/api/registry/manifest/newbanser-pristine-skill
LLM text
/api/registry/manifest/newbanser-pristine-skill?format=text
Install alias
/api/registry/install/newbanser-pristine-skill
Recommend
/api/registry/recommend?task=Use%20Pristine%20Skill%20in%20an%20agent%20workflow&limit=3
Agent fit
Coding agents
Use-case tags
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.
Agent decision cockpit
Companion skill for Coding agents
Shortlist this skill and compare it with close alternatives before production adoption.
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
- 1Install it in a sandbox agent and run one Coding agents task end to end.
- 2Compare output quality, latency, and failure behavior against at least one alternative.
- 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.
GitHub adoption
CHECK33 GitHub stars
Stars/forks activity
CHECK33 stars, 0 forks; issue activity unavailable in current metadata
Recent maintenance
PASS9d since push
License clarity
PASSMIT
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.
Workflow fit
Use this skill in these scenarios
Build and ship code
Coding agents
I need a coding agent that can understand a repository, edit code, and review pull requests.
Verify behavior
Testing and QA
I need my agent to test a web app, reproduce bugs, and verify fixes.
Investigate faster
Research agents
I need my agent to research a topic, compare sources, and produce a concise report.
Workflow fit
Add it to a complete workflow
Inspect, patch, and verify code
Coding review agent
A workflow for software agents that inspect repositories, review pull requests, generate tests, and turn findings into shippable patches.
Find, compare, and synthesize
Research report agent
A workflow for agents that gather sources, compare claims, summarize long material, and draft useful research briefs.
Design, build, test, and ship interfaces
Frontend and UI
A practical workflow for agents that turn product briefs or Figma designs into polished frontend code, review the result, test it in a browser, and prepare a safe deployment.
Alternative shortlist
Compare before you install
Similar skills that may fit this task.
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
Grill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
To Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
To Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
Overview
# Pristine
[English](README.en.md) | **简体中文**

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
Technical details
- Version
- 1.0.0
- License
- MIT
- Last updated
- Aug 18, 2026
- Published
- Aug 14, 2026
Frameworks & tools
Decision snapshot
Companion skill
recent repository activity
Audit
Install review
Install and adoption review
- Security
- 84/100
- Maintenance
- 100/100
- Install
- 92/100
Agent-proven evidence
Agent-proven evidence
Outcome reports after resolve, review, install, and one narrow run.
- 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
Scenario-led draft for Pristine Skill, ready for a manual X post.
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
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
This listing was indexed from public sources and is not marked official until a maintainer claim is approved.
- Creator
- newbanser
- Source
- newbanser/pristine-skill
- 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 skillOwner 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.
[](https://www.openagentskill.com/skills/newbanser-pristine-skill)
[](https://www.openagentskill.com/skills/newbanser-pristine-skill)
[](https://www.openagentskill.com/skills/newbanser-pristine-skill/audit)
[](https://www.openagentskill.com/skills/newbanser-pristine-skill)Author
newbanser
@newbanser
Platform fit
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
- 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
Related skills
Code Review
Review a branch or diff against repository standards and the originating spec in two independent analysis passes.
168.6K StarsGrill With Docs
A relentless interview that pressure-tests a plan against the codebase, sharpens domain language, and updates CONTEXT.md and ADRs when decisions become durable.
164.7K StarsTo Spec
Turn the current conversation and codebase context into a structured implementation spec, then publish it to the configured project issue tracker.
164.7K StarsTo Tickets
Break a plan, spec, or conversation into independently actionable tracer-bullet tickets with explicit blocking relationships.
176.7K Stars