agent-docs-maintainerSAFE
Documentation maintenance skills for Codex and Claude Code: README, planning, architecture, project guidance, and progress tracking.
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
简体中文
Minimal project progress and plan/spec storage, with shared document rules for explicit README, planning, architecture, guidance, and organization workflows.
This repository maintains the standalone plugin named agent-docs-maintainer for Codex and Claude Code. Client installation validation and release preparation remain pending; see remaining migration work.
Skills
- project-docs-bootstrap
- project-docs-refactor
- project-docs-readme
- project-docs-planning
- project-docs-architecture
- project-docs-guidance
- project-docs-progress
Edit sources/project-docs/ and run python3 scripts/buildprojectdocs.py --write. Root skills/ is generated; each installed skill includes its own referenced resources.
Installation
The GitHub repository is Laxpud/agent-docs-maintainer. The commands below describe the intended installation flow; actual installation and execution in both clients remain unverified. If the repository address changes, update publisher.homepage and publisher.repository in plugin-catalog.json and both README files, then regenerate metadata with --write.
Codex, in a terminal:
~~~bash codex plugin marketplace add Laxpud/agent-docs-maintainer ~~~
Then open the plugin picker and install agent-docs-maintainer:
~~~text /plugins ~~~
Claude Code, in the client input area:
~~~text /plugin marketplace add Laxpud/agent-docs-maintainer /plugin install agent-docs-maintainer@laxpud-agent-docs-maintainer ~~~
Start a new task or session after installation. Example prompt:
~~~text Use $agent-docs-maintainer:project-docs-bootstrap to initialize a minimal documentation baseline for this repository. ~~
b49e6698e764OBSERVED · 2026-10-12Host compatibility
What the documentation claims. We have not run a compatibility test.
| Host | Status | Notes |
|---|---|---|
| claude-code | mentioned | |
| codex | mentioned |
What it tells the agent
The instruction file, verbatim from the audited commit — this is the text the model reads, and the surface the audit's instruction layer examines. Quoted here so you can judge it without cloning anything.
--- name: project-docs-architecture description: Use only when explicitly invoked for architecture, technical mechanisms, source relationships, or ADRs. disable-model-invocation: true --- # 技术文档与架构 读取[共同约定](references/common-writing-rules.md),按任务选择下列规范;创建或实质重写时使用对应模板。 | 任务 | 先读规范 | 模板 | | --- | --- | --- | | 架构、组件、流程或源码关系 | [技术文档](references/architecture-rules.md) | [技术页](references/architecture-templates.md) | | 重要决定 | [ADR 规则与模板](references/architecture-adr-rules.md) | 内含示例 | 依据相关代码和配置说明当前实现;目标架构明确标为目标。文档工作不包含修改源码或重写 spec。
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- none-observed
- Network
- none-observed
- Shell
- none-observed
- Dependencies
- pinned
- Secrets in source
- none-found
Findings (1)
CLAUDE.md
Gates applied: no_behavioural_pass.
b49e6698e764full audit observations/trust-audit/skill/laxpud__agent-docs-maintainer.json · Report an issue / request a re-scanAudit history
Every audit this skill has had.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-12 | b49e6698e764 | SAFE | B | 89 | first audit |
Questions
What does the agent-docs-maintainer skill do?
Documentation maintenance skills for Codex and Claude Code: README, planning, architecture, project guidance, and progress tracking.
Is agent-docs-maintainer safe to install?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean skill reads B.
What can agent-docs-maintainer access on my machine?
The audit observed no filesystem, network or shell use at all in its source.
Which assistants does agent-docs-maintainer work with?
Its documentation mentions claude-code and codex. That is what the text claims, not a compatibility test we ran.
How current is this page?
The grade is for one exact copy of the source (b49e6698e764), read on 2026-10-12. The repository is watched, and a new audit runs when it changes — this is the first audit.