agentmods.dev

agent-native-scaffold

agent-native-scaffold is a skill for Claude Code, Codex from LFTPadilla/agent-dev-kit. It costs 51 tokens per session (851 once invoked), scanned A, original, MIT.

A tool for organizing software repositories so AI coding agents can find project information and files more reliably. It follows the ANRS-1.0 layout, including a central REGISTRY.yaml catalogue and shallow folders.

In plain words
What is it for?
Auditing a repository, creating its file and service catalogue, or reorganizing a new or legacy codebase for AI-assisted development.
Why use it?
It identifies and reduces problems such as oversized instruction files, missing project catalogues, deeply nested folders, and too much context for an agent to process.

Skill for Claude CodeCodex

Part of the dev-skills plugin — 24 skills, 1 command shipped together

not rated 2 6d ago A scan 51 tokens original MIT
View the source file LFTPadilla/agent-dev-kit
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/lftpadilla/agent-dev-kit/agent-native-scaffold
Any agent
npx skills add LFTPadilla/agent-dev-kit --skill agent-native-scaffold
Clone the repo
git clone --depth 1 https://github.com/LFTPadilla/agent-dev-kit

Made for: Claude Code, Codex.

Or install dev-skills, the plugin that ships this one along with the rest of its 24 skills, 1 command.

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 agent-native-scaffold

README.md
[![agentmods](https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/agent-native-scaffold.svg)](https://agentmods.dev/skills/lftpadilla/agent-dev-kit/agent-native-scaffold)
Your own site
<a href="https://agentmods.dev/skills/lftpadilla/agent-dev-kit/agent-native-scaffold"><img src="https://agentmods.dev/badge/skills/lftpadilla/agent-dev-kit/agent-native-scaffold.svg" alt="Measured on agentmods" height="20"></a>
Per session 51 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 851 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. 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 $0.00051 $0.00851
Opus 5 $0.00026 $0.00426
Sonnet 5 $0.00010 $0.00170
Haiku 4.5 $0.00005 $0.00085

Measured 3d ago against content hash 39d6ec4444ef, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agent-native-scaffold 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 3d 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.

plugins/dev-skills/skills/agent-native-scaffold/SKILL.md · 89 lines

How it starts

The opening of the file, as written. The whole thing — 89 lines — stays where its author put it; the contents beside it link to each section on GitHub.

agent-native-scaffold 🏛️

Transform greenfield or legacy software repositories into high-efficiency Agent-Native codebases adhering to the ANRS-1.0 specification.

When to invoke

  • User says: "Make this repo Agent-Native", "Organize this codebase for AI agents", "Audit repository context bloat".
  • Initializing a new repository or refactoring a legacy project with bloated root prompts.
  • When an AI agent experiences high tool hallucination or context rot.

When NOT to invoke

  • Single-script micro-tools with fewer than 5 files.
  • Modifying business logic without changing codebase architecture.

The Transformation Workflow

Phase 1: Audit & Discovery

Run the ANRS linter to inspect the target repository:

python3 scripts/audit-agent-native.py --repo-root <TARGET_DIR> --json

Analyze:

  1. Context Bloat: Is root AGENTS.md / CLAUDE.md > 150 lines?
  2. Catalog Presence: Is REGISTRY.yaml missing?
  3. Directory Depth: Are there paths nested deeper than 4 levels?

Phase 2: Generate Declarative Catalog (REGISTRY.yaml)

Create REGISTRY.yaml at the project root by cataloging:

  • Services: Ports, entrypoints, health check URLs.
  • MCP Servers: Tool schemas, executable paths, required env vars.
  • Skills: Custom capabilities and prerequisites.
  • Agents: Dedicated operational personas.

Use templates/agent-native/REGISTRY.yaml.template as baseline.

Phase 3: Construct Hub-and-Spoke Context (AGENTS.md)

  1. Root AGENTS.md (Hub):

    • Keep under 120 lines.
    • Encode non-negotiable invariants (Git worktree rules, SSoT for secrets/tasks).
    • Build the Semantic Routing Table pointing to subsystem guides.
    • Use templates/agent-native/AGENTS.md.template.

  2. Subsystem Contexts (Spokes):

Read the full file on GitHub · 89 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. 3d ago First seen · 89 lines · 51 tokens per session scan A 39d6ec4444ef

Subscribe to this mod's changes

agent-native-scaffold is a skill published in the GitHub repository LFTPadilla/agent-dev-kit (2 stars, last pushed 6d ago), licensed MIT. It adds 51 tokens to every session and 851 once invoked, about $0.0003 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.

Building agentsLLMagent-nativeagent-skillsai-agentsarchitectureclaude-codecontext-engineeringdeveloper-toolsrefactorscaffoldingskill
Related

Other skills, from other repositories

mandu-mcp-index

MCP 도구 오케스트레이션 라우터 (always-on). 108개 MCP 도구 중 상황에 맞는 워크플로우 skill 선택, 집계>세분 우선순위, anti-pattern 카탈로그. MCP 도구 호출 직전 자동 참조.

konamgil/mandu · 69 tokens

mandu-lint

Lint 가이드 — 가드레일의 한 축. oxlint 셋업 / 실행 / type-aware / lefthook 통합. "lint 켜줘", "코드 스타일 검사", lint 에러 발생 시 자동 호출.

konamgil/mandu · 53 tokens

mandu-mcp-create-flow

스펙 우선 생성 워크플로우. "만들어줘", 피처/리소스/라우트 추가 시 자동 호출. contract → generate 순서를 강제하고 생성 직후 verify loop 로 전이. granular 도구 (addroute + createcontract + generate) 를 손으로 엮지 않는다.

konamgil/mandu · 76 tokens

mandu-mcp-deploy

빌드/배포 파이프라인 워크플로우. "배포", "deploy", release 전 자동 호출. deploy.check 는 fail-fast 게이트. deploy.preview 로 프로덕션 리허설. manual build + guard + seo 나열 대신 aggregate 도구 사용.

konamgil/mandu · 65 tokens

mandu-mcp-verify

편집 후 검증 루프. 파일 편집 직후, "check 해줘", stop-hook 자동 호출. ateautopipeline + guardcheck + doctor 를 병렬로. 개별 ate 도구로 수동 분해 금지 — 실패했을 때만 drill-down.

konamgil/mandu · 66 tokens

mandu-mcp-orient

세션 시작 / 상태 파악 워크플로우. "현 상태", "무슨 일 있었어?", "어디서부터 시작?", 세션 재진입, 긴 대화 복귀 시 자동 호출. 개별 진단 도구를 순차 호출하지 않고 aibrief 로 집계한다.

konamgil/mandu · 72 tokens