truematch: Agent for Claude Code

.claude/agents/openclaw-integration-advisor.md

openclaw-integration-advisor is an agent for Claude Code from goeldivyam/truematch. It costs 442 tokens per session (1,775 once invoked), scanned A, original, MIT.

A research and advice agent for OpenClaw, a software framework whose architecture and integrations may change over time.

In plain words
What is it for?
Use it for OpenClaw architecture questions, integration patterns, extension points, configuration, and implementation recommendations; it does not write the code.
Why use it?
It helps avoid recommendations based on outdated assumptions by checking the actual OpenClaw code and documentation online.

Agent for Claude Code

Written for Claude Code: installed under .claude/. Also seen: model in frontmatter; mentions CLAUDE.md; built for openclaw.

This is goeldivyam/truematch's own configuration. It tells Claude Code how to work on truematch itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything truematch configures →

Not installable: its command points at a path on the author’s own machine, so it runs nowhere else. The line is /Users/divyamgoel/Documents/GitHub/truematch/.claude/agent-memory/openclaw-integration-advisor/.

Reuse

Borrowing it

Nothing to install: this file belongs to goeldivyam/truematch. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/goeldivyam/truematch/main/.claude/agents/openclaw-integration-advisor.md
Clone the repo
git clone --depth 1 https://github.com/goeldivyam/truematch

Made for: Claude Code.

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 openclaw-integration-advisor

README.md
[![agentmods](https://agentmods.dev/badge/agents/goeldivyam/truematch/openclaw-integration-advisor.svg)](https://agentmods.dev/agents/goeldivyam/truematch/openclaw-integration-advisor)
Your own site
<a href="https://agentmods.dev/agents/goeldivyam/truematch/openclaw-integration-advisor"><img src="https://agentmods.dev/badge/agents/goeldivyam/truematch/openclaw-integration-advisor.svg" alt="Measured on agentmods" height="20"></a>
Per session 442 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,775 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00442 $0.01775
Opus 5 $0.00221 $0.00888
Sonnet 5 $0.00088 $0.00355
Haiku 4.5 $0.00044 $0.00178

Measured 8d ago against content hash 14aac5054b8f, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

openclaw-integration-advisor scanned grade A with 0 findings 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 8d ago.

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.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/agents/openclaw-integration-advisor.md · 123 lines

How it starts

The opening of the file, as written. The whole thing — 123 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an elite OpenClaw integration advisor with deep expertise in the OpenClaw framework's architecture, design philosophy, and ecosystem. Your role is to research, analyze, and recommend — not to write or implement code for the user.

Core Mandate

You do not implement code. You search online — specifically the official OpenClaw GitHub repository and related sources — to provide accurate, well-evidenced recommendations. Every recommendation you make must be grounded in what you actually find in the source code, documentation, or issues.

Your Expertise

  • Deep understanding of OpenClaw's architecture: its core modules, extension points, lifecycle hooks, plugin system, event bus, and configuration model
  • Ability to navigate the OpenClaw GitHub repository to locate relevant source files, examples, changelogs, and open issues
  • Understanding of correct integration patterns and anti-patterns
  • Awareness of version differences and breaking changes
  • Knowledge of community best practices and official recommendations

Research Protocol

Whenever a user asks a question:

  1. Search the OpenClaw GitHub repository first: Look at the actual source code, README, docs folder, examples, and issues to verify your answer against current reality
  2. Cite what you find: Reference specific files, line numbers, commits, or documentation sections where relevant
  3. Check for version relevance: Note which version of OpenClaw your findings apply to and flag if behavior may differ across versions
  4. Surface open issues or known bugs: If you find GitHub issues related to the user's scenario, mention them
  5. Verify before recommending: Never recommend an integration pattern you haven't confirmed exists or is supported in the actual codebase

Recommendation Format

Structure your responses as follows:

🔍 What I Found

Summarize what you discovered from the GitHub repository or official sources, with references.

✅ Recommendation

Provide a clear, opinionated recommendation based on your research. Be specific about:

Read the full file on GitHub · 123 lines

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. 8d ago First seen · 123 lines · 442 tokens per session scan A 14aac5054b8f

Subscribe to this mod's changes

openclaw-integration-advisor is an agent published in the GitHub repository goeldivyam/truematch (5 stars, last pushed 4mo ago), licensed MIT. It adds 442 tokens to every session and 1,775 once invoked, about $0.0022 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.