repo-native-alignment: Agent for Claude Code

.claude/agents/gen-extractor.md

gen-extractor is an agent for Claude Code from open-horizon-labs/repo-native-alignment. It costs 26 tokens per session (2,786 once invoked), scanned A, original, MIT.

A generator for TOML configuration files that teach RNA how to detect data entering and leaving software boundaries. Examples include message brokers and event buses such as Google Pub/Sub, Redis, and RabbitMQ.

In plain words
What is it for?
Use it to describe publisher and subscriber patterns in natural language, generate extractor configurations, or scan a repository for missing coverage.
Why use it?
It fills gaps when the code-analysis system does not recognize a framework or communication pattern.

Agent for Claude Code

Written for Claude Code: installed under .claude/.

This is open-horizon-labs/repo-native-alignment's own configuration. It tells Claude Code how to work on repo-native-alignment 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 repo-native-alignment configures →

Reuse

Borrowing it

Nothing to install: this file belongs to open-horizon-labs/repo-native-alignment. 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/open-horizon-labs/repo-native-alignment/main/.claude/agents/gen-extractor.md
Clone the repo
git clone --depth 1 https://github.com/open-horizon-labs/repo-native-alignment

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 gen-extractor

README.md
[![agentmods](https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/gen-extractor/github.svg)](https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/gen-extractor)
Your own site
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/gen-extractor"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/gen-extractor/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for gen-extractor

Your own site · 80×15
<a href="https://agentmods.dev/agents/open-horizon-labs/repo-native-alignment/gen-extractor"><img src="https://agentmods.dev/badge/agents/open-horizon-labs/repo-native-alignment/gen-extractor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 2,786 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 $0.00026 $0.02786
Opus 5 $0.00013 $0.01393
Sonnet 5 $0.00005 $0.00557
Haiku 4.5 $0.00003 $0.00279

Measured 9d ago against content hash 8ff2c966f3a8, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

gen-extractor 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 9d 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/gen-extractor.md · 303 lines

How it starts

The opening of the file, as written. The whole thing — 303 lines — stays where its author put it; the contents beside it link to each section on GitHub.

/gen-extractor

Generate .oh/extractors/*.toml config files that teach RNA to detect Produces/Consumes edges for message brokers, event buses, and other boundary patterns.

Usage

/gen-extractor "detect Google Pub/Sub in Python — publisher.publish(topic_path) and subscriber.subscribe(subscription_path, callback)"
/gen-extractor "detect Redis pub/sub in Python — r.publish(channel, message) and r.subscribe(channel)"
/gen-extractor "detect RabbitMQ in Python — channel.basic_publish(exchange='', routing_key=topic, body=msg)"

Proactive mode — invoked without arguments: scans the repo for detected frameworks and flags gaps between what's detected and what's covered.

Config format

Every .oh/extractors/*.toml file must have this structure:

[meta]
name = "my-extractor"
applies_when = { language = "python", imports_contain = "some.library" }

[[boundaries]]
function_pattern = "client.publish"
arg_position = 0
edge_kind = "Produces"

[[boundaries]]
function_pattern = "client.subscribe"
arg_position = 0
edge_kind = "Consumes"

Fields:

  • meta.name — kebab-case identifier, matches the filename without .toml
  • meta.applies_when.language — exact language string as RNA stores it (e.g., "python", "go", "javascript", "typescript", "rust")
  • meta.applies_when.imports_contain — substring that must appear in at least one Import node's body or name for this config to activate. Use the most specific stable prefix of the library path (e.g., "google.cloud.pubsub" matches google.cloud.pubsub_v1).
  • boundaries[].function_pattern — substring of the call site to match, up to but NOT including (. RNA searches for function_pattern + "(" so "publisher.publish" matches publisher.publish( but not publisher.publish_to_dlq(.
  • boundaries[].arg_position — zero-indexed position of the argument that holds the topic/channel name as a quoted string literal. Use 0 for the first argument, 1 for the second, etc. Both arg_position and topic_arg are accepted (aliases).
  • boundaries[].edge_kind"Produces" (this code publishes/sends to the channel) or "Consumes" (this code subscribes/receives from the channel).
  • boundaries[].decorator — optional boolean, set true for decorator-based patterns (e.g., @bus.subscribe). Currently informational only — matching still uses body-text heuristics.

Read the full file on GitHub · 303 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. 9d ago First seen · 303 lines · 26 tokens per session scan A 8ff2c966f3a8

Subscribe to this mod's changes

gen-extractor is an agent published in the GitHub repository open-horizon-labs/repo-native-alignment (5 stars, last pushed today), licensed MIT. It adds 26 tokens to every session and 2,786 once invoked, about $0.0001 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.

Related

Other agents, from other repositories

Power Platform MCP Integration Expert

Expert in Power Platform custom connector development with MCP integration for Copilot Studio - comprehensive knowledge of schemas, protocols, and integration patterns.

github/awesome-copilot · 31 tokens

php-developer

Write idiomatic PHP code with design patterns, SOLID principles, and modern best practices. Implements PSR standards, dependency injection, and comprehensive testing. Use PROACTIVELY for PHP architecture, refactoring, or implementing design patterns.

davepoon/buildwithclaude · 51 tokens

backend-reviewer

Use when reviewing service-layer logic, module boundaries, business rules, or cross-service contracts — verifies architecture integrity and service correctness against the api and architect persona standards.

jeremylongshore/tons-of-skills-marketplace · 36 tokens

integrations-engineer

Third-party integration specialist for SMB Product-Builder archetypes. Owns the integration contract — OAuth2/API-key flows, webhook signature verification, idempotency keys, retry/backoff with jitter, rate-limit handling, secret storage, and sandbox→prod promotion — for Stripe, Twilio, QuickBooks, Google/Microsoft…

avelikiy/great_cto · 106 tokens

gate

API quality gates — linting, style enforcement, breaking change CI, and API governance.

tonone-ai/tonone · 19 tokens

dotnet-architecture-reviewer

Reviews a .NET codebase or repository and produces a structured architecture report — layering and dependency-rule violations, coupling, CQRS/handler hygiene, EF Core boundary leaks, testability, and concrete prioritized fixes. Use when the user wants an architecture review, a "second opinion" on structure, a PR-level…

StefanTheCode/dotnet-ai-toolkit · 102 tokens