Borrowing it
Nothing to install: this file belongs to webmaxru/is-ai-native. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/webmaxru/is-ai-native/main/.github/agents/assistant-config-curator.agent.mdgit clone --depth 1 https://github.com/webmaxru/is-ai-nativeWrote 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.
[](https://agentmods.dev/agents/webmaxru/is-ai-native/assistant-config-curator)<a href="https://agentmods.dev/agents/webmaxru/is-ai-native/assistant-config-curator"><img src="https://agentmods.dev/badge/agents/webmaxru/is-ai-native/assistant-config-curator/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.
<a href="https://agentmods.dev/agents/webmaxru/is-ai-native/assistant-config-curator"><img src="https://agentmods.dev/badge/agents/webmaxru/is-ai-native/assistant-config-curator.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00018 | $0.01100 |
| Opus 5.5 | $0.00007 | $0.00440 |
| Sonnet 5.5 | $0.00004 | $0.00220 |
| Haiku 4.5 | $0.00002 | $0.00110 |
Grade A, and why
assistant-config-curator 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 1mo 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.
How it starts
The opening of the file, as written. The whole thing — 114 lines — stays where its author put it; the contents beside it link to each section on GitHub.
User Input
$ARGUMENTS
You MUST consider the user input before proceeding.
Purpose
Maintain the repository's assistant capability model so that:
packages/core/config/primitives.jsonstays aligned with official repository-scoped customization resourcespackages/core/config/assistants.jsonstays aligned with current official assistant landing pages and documentation URLsdocs/configuration.mdremains synchronized with the scanner and includes a specific source link for every primitive and assistant row- new vendor-documented capabilities are either mapped to an existing primitive or introduced as a new primitive only when they are meaningfully distinct
This agent leverages both saved prompts already in the repository:
Treat those prompts as reusable operating policies. This agent is the orchestrator that chooses which workflow to run and when to combine them.
Operating Modes
1. Maintenance Mode
Use this when the request is about drift detection, stale links, changed documented file paths, or keeping existing primitives current.
Follow the policy from review-assistant-config-sources.prompt.md:
- compare official docs from the
URLs To Monitorsection of docs/configuration.md against packages/core/config/primitives.json and packages/core/config/assistants.json - update scanner patterns only when vendor docs clearly support repository-scoped files
- keep scanning limited to shareable repo files
- update primitive
docLinks, assistant metadata links, and the configuration docs together - call out proxy scanning cases such as
.codex/config.toml - run relevant backend tests if scanner patterns change
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.
- 1mo ago First seen · 114 lines · 18 tokens per session scan A e371c1f4ed24
assistant-config-curator is an agent published in the GitHub repository webmaxru/is-ai-native (5 stars, last pushed 2mo ago), licensed MIT. It adds 18 tokens to every session and 1,100 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other agents, from other repositories
04g-Governance
Azure governance discovery agent. Queries Azure Policy assignments via REST API (incl. management-group-inherited policies), classifies effects, produces governance constraint artifacts, and runs adversarial review. Step 3.5: after Architecture, before IaC Planning.
06b-Bicep CodeGen
Expert Azure Bicep IaC specialist that creates near-production-ready Bicep templates following Azure Verified Modules (AVM) standards. Validates, tests, and ensures code quality.
03-Architect
Expert Architect providing guidance using Azure Well-Architected Framework principles and Microsoft best practices. Evaluates decisions against WAF pillars and generates Azure MCP-priced cost estimates.
01-Orchestrator
Coordinate approved Azure platform work in VS Code Copilot. Recover project state, collect material decisions, delegate bounded specialist tasks and preserve reviews, governance and consequential approvals.
08-As-Built
Generate evidence-led as-built documentation, deployed SKU drift and cost estimates in VS Code Copilot. Query actual state; preserve planned decisions and report gaps without repairing infrastructure.
11-Context Optimizer
Audit scoped Copilot context/usage evidence or agent source and recommend improvements. Measured telemetry is distinct from source-size estimates. Recommendations only; never edits agents, skills or instructions.