new-agents-md

new-agents-md is a skill for Claude Code from AcKeskin/contexture. It costs 78 tokens per session (4,630 once invoked), scanned A, original, MIT.

A generator that turns Claude Code instructions into an AGENTS.md file, a vendor-neutral guide that other coding agents can read.

In plain words
What is it for?
It helps project teams share repository instructions across different coding-agent tools and asks questions only where the source instructions are incomplete.
Why use it?
It prevents agents such as Codex, Cursor, or Aider from missing the project’s commands, rules, and known hazards.

Skill for Claude Code

Written for Claude Code: SessionStart hook event. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

Good fit It helps project teams share repository instructions across different coding-agent tools and…

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/ackeskin/contexture/new-agents-md
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.

Any agent
npx skills add AcKeskin/contexture --skill new-agents-md
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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 new-agents-md

README.md
[![agentmods](https://agentmods.dev/badge/skills/ackeskin/contexture/new-agents-md.svg)](https://agentmods.dev/skills/ackeskin/contexture/new-agents-md)
Your own site
<a href="https://agentmods.dev/skills/ackeskin/contexture/new-agents-md"><img src="https://agentmods.dev/badge/skills/ackeskin/contexture/new-agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 78 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 4,630 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 $0.00078 $0.04630
Opus 5 $0.00039 $0.02315
Sonnet 5 $0.00016 $0.00926
Haiku 4.5 $0.00008 $0.00463

Measured 3d ago against content hash 15a678599818, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

new-agents-md 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.

skills/new-agents-md/SKILL.md · 368 lines

How it starts

The opening of the file, as written. The whole thing — 368 lines — stays where its author put it; the contents beside it link to each section on GitHub.

new-agents-md

The cross-tool projection organ. Closes the gap that the entire instruction surface here is Claude-Code-exclusive: CLAUDE.md, the @claude-md/... imports, the ~/.claude/architectural-rules/ loader, the typed-memory warning/feedback corpus, and every skill are invisible to any other coding agent. The moment a non-Claude agent (Codex, Cursor, Aider, Continue, Zed) is pointed at a repo, it starts blind and guesses exactly what the corpus already pins — test commands, package manager, the "never commit AI attribution" landmine, the architectural defaults.

This skill projects the lean corpus into a vendor-neutral, repo-root AGENTS.md (plus a global one) that those agents read on session start. It is a distill-then-interview organ: it reads the corpus and proposes a draft before asking anything, then interviews only for what no corpus read can supply.

When to run

  • User types /new-agents-md (explicit trigger).
  • User says "generate an AGENTS.md," "make this repo readable by Codex/Cursor/Aider," "scaffold cross-tool instructions," "I want a vendor-neutral agents file."
  • Do not auto-fire. No session-start or event-hook triggers. Mode A only — every run goes through the full distill + interview. (Trigger lives in the frontmatter description per universal/skill-auto-fire.md; there is no SessionStart hook.)

Why this skill exists

The cross-tool convention is AGENTS.md — a vendor-neutral, repo-root instruction file. The naive fix from the convention's write-ups is "make AGENTS.md canonical and reduce CLAUDE.md to a thin @AGENTS.md stub." That stub-inversion is rejected here. The value of this environment lives in machinery a generic agent cannot execute — on-demand rule loading, discovery/prep organs, typed memory, skills. A generic reader can run none of it, so AGENTS.md cannot @import the essentials; it must carry a flattened, behaviour-only projection of the corpus.

Hand-maintaining that projection beside the live corpus would reintroduce the duplication that single-source-of-truth exists to avoid — a stale hand-copied AGENTS.md is worse than none. So AGENTS.md is treated as a derived artefact (like a codemap: regenerate on demand), not a hand-maintained twin (like memory: authored, versioned). This skill is the generator.

Read the full file on GitHub · 368 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 · 368 lines · 78 tokens per session scan A 15a678599818

Subscribe to this mod's changes

new-agents-md is a skill published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 78 tokens to every session and 4,630 once invoked, about $0.0004 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 2026-09-03.