Legal Harness Initializer

What it does

When your agent uses it

• Creating a baseline AGENTS.md or CLAUDE.md for a lawyer or legal team
• Updating managed instruction blocks without overwriting your own text
• Separating personal, project and organization level agent rules
• Verifying in a fresh session that confidentiality and permission rules are followed

Example prompts

• “Set up an AGENTS.md baseline for my litigation practice with strict privacy mode.”
• “Update the managed block in our team CLAUDE.md and show me a dry run diff first.”
• “Initialize agent rules for our in-house legal team across the organization, project and personal levels.”
• “Verify that a new session loaded the instructions and passes the behavior probes.”

Requirements

• Bash to run the detection and write scripts
• A coding agent harness that reads AGENTS.md or CLAUDE.md

Workflow steps

3 steps, taken from the first numbered list in SKILL.md.

1. 1CONFIG_WRITTEN：文件与受管区块存在。
2. 2INSTRUCTIONS_LOADED：新会话报告了精确加载来源。
3. 3BEHAVIOR_VERIFIED：新会话通过四类行为探针。

What it can do on your machine

Read from SKILL.md and the folder at commit f844ebe. It shows what the files ask for, not the result of running them.

• Tool permissions

  Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

  From allowed-tools in the SKILL.md frontmatter.

• Runs code

  Ships 1 file in scripts/, which the agent can run.

  Shell commands in SKILL.md call:

  • bash
  • claude
  • codex

  From the folder's file list and the shell code blocks in SKILL.md.

• Network

  No URLs in SKILL.md.

  From URLs in SKILL.md, links to its own repository left out.

• Credentials

  Names no API keys, tokens, secrets or passwords.

  From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Legal Harness Initializer loads about 2.3k tokens when it runs, and up to ~27k if it reads all its reference files. Until then it costs about 58 tokens; SKILL.md has 471 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it

~58

When it runs · the whole SKILL.md, loaded when a task matches

~2.3k

With references · SKILL.md plus every file in references/, read only if the agent opens them

~27k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from cat-xierluo/legal-skills at commit f844ebe, republished under its MIT licence (© cat-xierluo). 471 words, ~2,259 tokens.

name

legal-harness-init

description

面向法律工作者初始化或增量治理 AGENTS.md/CLAUDE.md：识别当前 AI harness，区分用户级、项目级和团队级指令，生成最小法律安全基线，安全合并受管区块，并在新会话中验证权限、保密、信息缺口和回溯行为。用户明确提到法律工作且要配置 harness、AGENTS.md、CLAUDE.md、agent 协作规则或 AI 使用基线时使用。不要用于合同审查、案件分析、文书起草、项目脚手架或 Skill 开发。

version

0.5.2

license

MIT

author

杨卫薪律师（微信ywxlaw）

homepage

https://github.com/cat-xierluo/legal-skills

<!-- skill-lint:constraint COMPLETION-STATUS-NO-OVERCLAIM -->

bash scripts/detect.sh
# 调用方明确知道当前平台时：
bash scripts/detect.sh --runtime codex

<!-- skill-lint:constraint TEAM-LAYER-PRECEDENCE -->

<!-- skill-lint:constraint PRIVACY-MINIMUM-CONTEXT -->

# 项目：{项目代号}

- 类型：{项目类型}
- 阶段：{当前阶段}
- 关键时点：{日期 + 事项；未知则写待补充}
- 受控事实入口：{不需要则写“无”}
- 文件结构与权威载体：{沿用项目现有约定}

<!-- skill-lint:constraint MANAGED-BLOCK-SAFE-UPSERT -->

bash scripts/validate-content.sh \
  --file <模块内容文件> \
  --privacy-mode <strict|local|team>

bash scripts/write.sh \
  --content-file <模块内容文件> \
  --level <user|project> \
  --platforms <key,key> \
  --mode <create|update|append> \
  --block-id <稳定-id> \
  --privacy-mode <strict|local|team> \
  --project-dir <项目路径> \
  --dry-run

bash scripts/restore.sh --target <AGENTS.md-or-CLAUDE.md>

bash scripts/record-init-env.sh \
  --target <项目/AGENTS.md|CLAUDE.md> \
  --action <init|update|append> \
  [--model <model-name>] \
  [--harness <key>] \
  [--harness-version <v>] \
  [--skill-version <v>] \
  [--note "<额外说明>"] \
  [--probe-from-session] \
  [--dry-run]

<!-- skill-lint:constraint INIT-ENVIRONMENT-RECORD-ON-WRITE -->

bash scripts/verify.sh \
  --target <配置文件> \
  --block-id <稳定-id> \
  --session-evidence <证据文件>

bash scripts/test.sh

© cat-xierluo, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 61 other files (scripts, references, assets) in skills/legal-harness-init of cat-xierluo/legal-skills.

• SKILL.md
• CHANGELOG.md
• LICENSE.txt
• agents/openai.yaml
• assets/audit-trail-snippet.md
• assets/quick-baseline-example.md
• assets/stability-complete.json
• assets/stability-duplicate-marker.json
• assets/stability-overclaim.json
• assets/stability-sensitive.json
• assets/stability-wrong-precedence.json
• config/instruction-stability-contract.json
• references/01-why-agents-md-matters.md
• references/02-user-vs-project-level.md
• references/03-harness-detection.md
• references/04-modules.md
• references/05-write-an-agents-md.md
• … and 45 more

Open the folder on GitHubat commit f844ebe