🧾
QualityJavaScript

Audit Session

by devcodex-labs

Audit Session is a Quality skill for Claude Code, published by devcodex-labs in devcodex.

202 stars26 forkson devcodex-labs/devcodexAdded 2026/09/05+16% in starsRepository updated 2026/08/31
ai-codingclaude-codecodexcoding-agentcursordeveloper-toolsgemini-cligithub-copilotgroklocal-firstworkflow-runtime
Install in seconds
Install Audit Session
Copy Audit Session into your Claude Code skills folder. Run the command in your terminal, or review the source on GitHub before installing.
terminal
npx degit https://github.com/devcodex-labs/devcodex/tree/main/content/skills/audit-session ~/.claude/skills/audit-session

Requires Node.js. Downloads this skill only — not the rest of the repository — into your Claude Code skills folder.

Without Node.js

git clone https://github.com/devcodex-labs/devcodex.git

Clones the whole repository, then copy the skill’s own directory into your skills folder yourself.

In this catalog

Source file
content/skills/audit-session/SKILL.md in devcodex-labs/devcodex
Installs to
~/.claude/skills/audit-session
Collection
One of 25 skills cataloged from this repository
Category
Quality1662 skills

What Audit Session does

Audit Session persists audit rounds, findings, and convergence state in a session JSON file so an audit can resume after interruption. Use it for multi-round audit workflows that need exact recovery across sessions.

Audit Session is cataloged under Quality on DirSkills. Audit Session comes from a repository tagged ai-coding, claude-code, codex, coding-agent and cursor.

Documentation

README

Audit Session Skill

适用范围

  • 触发:意图为 audit 且预期轮次 ≥3(即所有非 chat 审计场景)
  • 不适用:analyze(仅 ≥3 轮收敛但无 audit finding 交接状态机)、chat(无审计语义)

状态文件路径

<audit-root>/.audit-state/<session-id>.json

<audit-root> 取值:

  • 旧布局:<项目根>/.devcodex

  • 集中布局单项目:<工作区根>/.devcodex/<project>

  • 集中布局全工作区:<工作区根>/.devcodex/workspace

  • <session-id> 取首次启动审计的时间戳:YYYYMMDD-HHmmss

  • <audit-root>/.audit-state/ 目录由本 Skill 首次写入时创建(不随 init 分发)

  • .gitignore 须覆盖 <audit-root>/.audit-state/ 对应路径(如 .devcodex/.audit-state/.devcodex/*/.audit-state/,同记忆策略)

状态机

active ──┬─> paused (Token 防护触发 / 用户中断)
         ├─> resumed (跨会话 resume 重新进入)
         ├─> converged (CRS + PCV 通过 + 连续3轮零发现)
         └─> closed (用户确认审计闭环)

paused ──> resumed ──> active
converged ──> closed

This is the opening of the README. Read the full README on GitHub.

Frequently asked about Audit Session

  • What else does devcodex-labs publish alongside Audit Session?

    Audit Session is one of 25 skills that DirSkills catalogs from devcodex-labs/devcodex, the repository it ships in. Its siblings there include AI Agent System Architecture, AI Evaluation Engineering and API Contract Architecture. Each one is a separate skill with its own page in this directory, installs the same way Audit Session does, and is maintained by devcodex-labs in that same repository. The rest of the collection is listed on the devcodex-labs/devcodex page.

  • How does Audit Session compare to other Quality skills?

    Audit Session ranks #1517 by stars among the 1662 Quality skills in this catalog. The most-starred ones next to it are Benchmark, Benchmark Optimization Loop and API Design Patterns. DirSkills ranks by the star count of the repository each skill ships in, so that order reflects how popular those repositories are rather than any review of Audit Session against them. Open each page to compare what they document and how they install.

More from devcodex-labs/devcodex

Audit Session is one of 25 skills cataloged on DirSkills from devcodex-labs/devcodex.

See all 25 skills
🤖
46m ago

AI Agent System Architecture

AI Agent System Architecture covers agent routing, tool permissions, context, memory, state, and observability for tasks that need explainable and auditable agent behavior. Use it when designing agent workflows, recovery, handoff, or model-assisted governance.
AI Engineering
20226
🧪
46m ago

AI Evaluation Engineering

AI Evaluation Engineering designs evidence for model and prompt quality using golden sets, rubrics, judge calibration, repeat sampling, variance reporting, and regression decisions. Use it when comparing models, prompts, or upgrades and you need reproducible results with contamination checks.
AI Engineering
20226
🧩
46m ago

API Contract Architecture

API Contract Architecture defines and freezes public API contracts before implementation. Use it for HTTP, SDK, CLI, schema, error, pagination, idempotency, and compatibility changes that affect consumers.
AI Engineering
20226
🌐
47m ago

Accessibility I18n

Accessibility I18n handles accessibility and localization review for user-facing UI, CLI output, and docs. Use it when tasks involve keyboard flow, focus, screen readers, ARIA, RTL, translations, locale formats, or multilingual content.
Frontend
20226
🔍
46m ago

Analyze Default

Analyze Default defines a read-only workflow for multi-round code analysis, evidence gathering, and convergence checks. Use it when you need a factual conclusion, root-cause assessment, or review of whether something is correct without changing files.
Quality
20226
🔬
46m ago

Analyze Research

Analyze Research handles technical selection, feasibility checks, dependency comparisons, and root-cause investigation in a read-only workflow. Use it when you need evidence-based recommendations without changing source files.
AI Engineering
20226