agent-ready-web-profile: Instructions file for Codex

AGENTS.md

agent-ready-web-profile AGENTS.md is an instructions file for Codex, OpenCode from dkharlanau/agent-ready-web-profile. It costs 2,269 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for coding agents working on an agent-ready website project. It describes the project's workflows, supported discovery methods, setup commands, and checks.

In plain words
What is it for?
Use it to guide agents through website discovery work, growth experiments, installation, testing, and maturity checks.
Why use it?
It gives coding agents project-specific rules and verification steps instead of making them infer how the repository works.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md.

This is dkharlanau/agent-ready-web-profile's own configuration. It tells Codex and OpenCode how to work on agent-ready-web-profile 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 agent-ready-web-profile configures →

Reuse

Borrowing it

Nothing to install: this file belongs to dkharlanau/agent-ready-web-profile. 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/dkharlanau/agent-ready-web-profile/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/dkharlanau/agent-ready-web-profile

Made for: Codex, OpenCode.

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-ready-web-profile AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/dkharlanau/agent-ready-web-profile/agents-md.svg)](https://agentmods.dev/instructions/dkharlanau/agent-ready-web-profile/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/dkharlanau/agent-ready-web-profile/agents-md"><img src="https://agentmods.dev/badge/instructions/dkharlanau/agent-ready-web-profile/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 2,269 This file is loaded in full into every session.
When invoked 2,269 The same file — it is already loaded in full.
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 $0.02269 $0.02269
Opus 5 $0.01135 $0.01135
Sonnet 5 $0.00454 $0.00454
Haiku 4.5 $0.00227 $0.00227

Measured today against content hash 320b5910bda9, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-08, from the pricing page.

Security

Grade A, and why

agent-ready-web-profile 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 today.

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.

AGENTS.md · 128 lines

How it starts

The opening of the file, as written. The whole thing — 128 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Agent-Ready Web Profile — agent instructions

ARWP has four connected layers:

  1. Growth Loop — primary operational workflow. Research current Search/recommendation/AI changes, classify the evidence, turn applicable mechanisms into explicit hypotheses, inspect a target website, implement the highest-confidence changes, verify them and measure owner-side outcomes.
  2. Search Maturity Benchmark — governed reference-comparison workflow. Observe currently visible independent pages for a real intent, profile only evidence that was actually reviewed, identify repeated cohort patterns and compare those patterns with a target site without relabeling correlations as ranking factors.
  3. Future Search Lab — governed experimental workflow. After current foundations are healthy, explore truthful open-web semantics, entity/evidence graphs, retrieval feedback and browser-agent operability that may matter to future Search/AI systems even when no current ranking benefit is documented.
  4. Resolver / interoperability foundation. Discover how a public website can actually be read, searched or operated by agents without requiring universal adoption of an ARWP-specific manifest.

The optional publisher profile, Resolver, scanner, benchmarks, gateways, evidence receipts and protocol work remain supported. The broader Search/Future scope does not license speculative ranking claims or indiscriminate metadata growth.

Install and verify

npm ci
npm test
npm run quickstart
node scripts/growth-hypotheses-test.mjs
node bin/arwp-hypotheses.mjs check
node bin/arwp-trends.mjs check
node scripts/future-search-test.mjs
node benchmarks/search-maturity-test.mjs
node bin/arwp-search-maturity.mjs check benchmarks/search-maturity/pilot-2026-09-07.json
node scripts/maturity-profile-test.mjs --site
node bin/arwp-maturity.mjs check docs/maturity/profile.json

Agent Skills routing

  • arwp-growth-loopdefault for Search growth, Discover/recommendations, generative Search/AI citations, current platform adaptation or ongoing website improvement.
  • arwp-search-maturity — competitive/reference reverse-engineering, high-visibility reference cohorts, fast-riser analysis and evidence-bearing target-vs-reference gaps.
  • arwp-prepare-site — initial technical preparation/adoption of an existing website repository.
  • arwp-adaptive-upgrade — compile applicable current evidence into target-specific change contracts.
  • arwp-target-transformation — resolve grounded upgrades to exact target files and reviewable deterministic changes.
  • arwp-ai-search-content — useful, original, evidence-backed content.
  • arwp-future-search — governed future-ready semantics, semantic/evidence graphs, retrieval feedback and browser-agent operability beyond today's documented Search feature set.
  • arwp-agent-discovery — truthful llms.txt, Agent Skills, ARD, OpenAPI/MCP/A2A/WebMCP and ARWP surfaces.
  • arwp-evidence-ci — assertions, scheduled audits, receipts and drift-safe CI.

Read the full file on GitHub · 128 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. today Changed · +41 lines · +1,059 tokens per session 320b5910bda9
  2. yesterday First seen · 87 lines · 1,210 tokens per session scan A 847522c8e30d

Subscribe to this mod's changes

agent-ready-web-profile AGENTS.md is an instructions file published in the GitHub repository dkharlanau/agent-ready-web-profile (0 stars, last pushed today), licensed Apache-2.0. It adds 2,269 tokens to every session, about $0.0113 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 2026-09-07.

Related

Other instructions, from other repositories