adapter-claudecode

adapter-claudecode is a skill for Claude Code, Codex from Tyox-all/Weave_Protocol. It costs 116 tokens per session (1,050 once invoked), scanned A, original, Apache-2.0.

An adapter that applies WARD.md security rules to Claude Code, an AI coding tool, before it uses tools.

In plain words
What is it for?
Use it to install, inspect, test, disable, or enforce WARD policies in Claude Code sessions.
Why use it?
It can block actions that violate project or global rules, helping limit an agent’s access to sensitive files and operations.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/tyox-all/weave_protocol/adapter-claudecode
Any agent
npx skills add Tyox-all/Weave_Protocol --skill adapter-claudecode
Clone the repo
git clone --depth 1 https://github.com/Tyox-all/Weave_Protocol

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for adapter-claudecode

README.md
[![agentmods](https://agentmods.dev/badge/skills/tyox-all/weave_protocol/adapter-claudecode.svg)](https://agentmods.dev/skills/tyox-all/weave_protocol/adapter-claudecode)
Your own site
<a href="https://agentmods.dev/skills/tyox-all/weave_protocol/adapter-claudecode"><img src="https://agentmods.dev/badge/skills/tyox-all/weave_protocol/adapter-claudecode.svg" alt="Measured on agentmods" height="20"></a>
Per session 116 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,050 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00116 $0.01050
Opus 5 $0.00058 $0.00525
Sonnet 5 $0.00023 $0.00210
Haiku 4.5 $0.00012 $0.00105

Measured 4d ago against content hash 2b756df71c48, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

adapter-claudecode scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

The scan reads SKILL.md. This mod also ships 5 executable files (src/cli.ts, src/config.ts, src/hook.ts, …), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Reads agent configuration directorieslowAgent snooping

.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.

description: Use this skill when the user wants to enforce a WARD.md security policy inside Claude Code via its native hook system. Triggers on requests to "secure my Claude Code session", "block Claude Code from doing X

Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.

adapter-claudecode/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Claude Code adapter for Weave Protocol

The @weave_protocol/adapter-claudecode package enforces WARD.md policies inside Claude Code via the PreToolUse hook system. When Claude Code is about to use a tool, the adapter reads the active WARD.md and blocks the call if it violates the policy.

When to use

  • User runs Claude Code and wants visibility/control over what it does
  • User has a WARD.md and wants it enforced inside Claude Code (not just on MCP servers)
  • User wants to lock down a sensitive project so Claude Code can't escape its bounds
  • User has a global ~/.claude/WARD.md they want applied to every session
  • User wants to test what their WARD policy would do before deploying it

Commands

weave-claude-code init [--matcher=X] [--fail-closed]    # Install hook
weave-claude-code disable                                # Remove hook
weave-claude-code status                                 # Show config + active policy
weave-claude-code test <tool> [--input=JSON]             # Dry-run a tool call
weave-claude-code help

WARD resolution order

When the hook fires:

  1. $WEAVE_WARD_PATH — explicit override
  2. <cwd>/WARD.md — project root
  3. <cwd>/.weave/WARD.md — alternate location
  4. ~/.claude/WARD.md — user-global fallback

First match wins. If none exists, the hook passes through silently.

Tool mapping

Claude Code → WARD capability:

  • Bashshell_exec (also scans command string heuristically)
  • Edit, MultiEdit, Writefile_write
  • Readfile_read
  • Grep, LS, Globfile_read / file_list
  • WebFetchhttp_request (checks url)
  • WebSearchweb_search
  • Tasksubagent
  • NotebookEditnotebook_edit

WARD.md can use either the literal Claude tool name (e.g., Bash) or the generic capability (shell_exec). The stricter rule wins.

Decision rules

Situation Action
User wants to enforce WARD in Claude Code weave-claude-code init
User wants to test their policy weave-claude-code test <tool>
User wants global policy across all projects Write ~/.claude/WARD.md
User wants project-specific policy Write <project>/WARD.md
User wants stricter failure mode init --fail-closed
User wants to uninstall weave-claude-code disable
User reports Claude Code blocked unexpectedly weave-claude-code status (shows active policy and source)

Read the full file on GitHub · 84 lines

Files

What ships with it

10 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 84 lines · 116 tokens per session scan A 2b756df71c48

Subscribe to this mod's changes

adapter-claudecode is a skill published in the GitHub repository Tyox-all/Weave_Protocol (0 stars, last pushed 11d ago), licensed Apache-2.0. It adds 116 tokens to every session and 1,050 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

rtc-balance

Check RustChain wallet balance, epoch info, and network status via the public RPC.

Scottcjn/Rustchain · 20 tokens

panguard

AI agent security platform — audit skills, scan for threats, and run 24/7 protection with 9,700+ detection rules.

panguard-ai/panguard-ai · 30 tokens

blockchain-solana

Use this skill when asked about Solana blockchain, Solana architecture, Proof of History, Solana programming, Anchor framework, Solana runtime, Solana CLI tools, Solana DeFi, Jupiter, Raydium, Metaplex, SPL tokens, and the Solana ecosystem. Covers Solana protocol architecture (PoH, Tower BFT, Turbine, Gulf Stream…

j4flmao/agent-skills · 142 tokens

lictor-security-check

Pre-release security audit for ANY project — AI-built or hand-written, web or mobile. Scans the codebase for the full range of real-world risks that get apps breached: leaked API & AI-provider keys, exposed configs/secrets, broken auth & access control (IDOR), injection (SQL/XSS/command), SSRF, open databases & cloud…

Raffa-jarrl/Lictor-AI · 135 tokens

lictor-rotate

Walks the user through rotating a leaked API key — step by step, provider-specific. Knows the exact URL to visit, the exact button to click, and how to verify the rotation worked. Supports Stripe, OpenAI, Anthropic, Google Cloud / AI Studio, GitHub, AWS, Slack, Supabase, Firebase, Postmark, and generic OAuth providers.

Raffa-jarrl/Lictor-AI · 80 tokens

alchemy-agentic-gateway

Use when accessing Alchemy APIs for RPC calls, token balances, NFT metadata, asset transfers, transaction simulation, or Alchemy-specific features. Also use when the user mentions "SIWE", "SIWS", "x402", "MPP", "mppx", or "agentic gateway" — this skill covers wallet-based auth flows for Alchemy's x402 and MPP…

moonpay/skills · 101 tokens