new-agents-md

new-agents-md is a command for coding agents from AcKeskin/contexture. It costs 66 tokens per session (459 once invoked), scanned A, original, MIT.

A command that turns Claude Code’s project instructions into an AGENTS.md file, a shared instruction file that other coding agents can read. It also asks questions about details the existing instructions do not contain.

In plain words
What is it for?
Use it to create or update repository and global AGENTS.md files for tools such as Codex, Cursor, or Aider. It also helps identify missing development commands and project-specific restrictions.
Why use it?
It removes the need to rewrite project rules for each coding tool. It helps other agents follow the repository’s conventions, commands, warnings, and architecture guidance.

Command

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 commands/ackeskin/contexture/new-agents-md
Clone the repo
git clone --depth 1 https://github.com/AcKeskin/contexture

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/commands/ackeskin/contexture/new-agents-md.svg)](https://agentmods.dev/commands/ackeskin/contexture/new-agents-md)
Your own site
<a href="https://agentmods.dev/commands/ackeskin/contexture/new-agents-md"><img src="https://agentmods.dev/badge/commands/ackeskin/contexture/new-agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 66 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 459 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 $0.00066 $0.00459
Opus 5 $0.00033 $0.00230
Sonnet 5 $0.00013 $0.00092
Haiku 4.5 $0.00007 $0.00046

Measured 4d ago against content hash 2245628ed5c6, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 4d 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.

commands/new-agents-md.md · 23 lines

What it actually says

Run the new-agents-md skill.

Forms:

  • /new-agents-md — distill the corpus into a draft repo-root AGENTS.md (and a global one), then interview for the gaps.

Examples:

  • /new-agents-md — "make this repo readable by non-Claude agents."
  • Natural language: "create an AGENTS.md", "generate cross-tool instructions", "let Codex/Cursor read our conventions."

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. This skill is a distill-then-interview organ: Pass 1 reads the lean corpus (CLAUDE.md tree + always-tier architectural rules after tier-overlay resolution + warning/feedback landmines + canonical commands) and proposes a draft before asking anything; Pass 2 interviews only for what no corpus read can supply (exact dev/test commands, repo-specific "never X", architecture orientation, infra hints), routing surfaced landmines back through /capture so the projection feeds the source.

It rejects the stub-inversion (the Claude loader is Claude-specific) — AGENTS.md carries a flattened behaviour-only projection, derived not twinned (regenerate on demand; drift is surfaced by review, not enforced). Complementary to the deterministic project-instructions projector and seamed to the org rule tier.

Does not auto-fire. Not a hand-maintained twin of CLAUDE.md, not a Claude-side change (Claude doesn't read AGENTS.md).

See ~/.claude/skills/new-agents-md/SKILL.md for the full procedure.

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. 4d ago First seen · 23 lines · 66 tokens per session scan A 2245628ed5c6

Subscribe to this mod's changes

new-agents-md is a command published in the GitHub repository AcKeskin/contexture (2 stars, last pushed 1mo ago), licensed MIT. It adds 66 tokens to every session and 459 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.