awesome-ai-devtools AGENTS.md

awesome-ai-devtools AGENTS.md is an instructions file for Codex, OpenCode from yeaight7/awesome-ai-devtools. It costs 344 tokens per session, scanned A, original, MIT.

Repository instructions for awesome-ai-devtools, a catalogue whose tool listings are generated from YAML data files. They define where metadata belongs and how listings are sorted, generated, and tested.

In plain words
What is it for?
Use them when adding or updating tool entries, categories, or tags, importing candidate tools, regenerating documentation, or running validation.
Why use it?
They prevent edits from being lost in generated files and reduce inaccurate or promotional catalogue information.

Instructions file for CodexOpenCode

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 instructions/yeaight7/awesome-ai-devtools/agents-md
Clone the repo
git clone --depth 1 https://github.com/yeaight7/awesome-ai-devtools

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 awesome-ai-devtools AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/yeaight7/awesome-ai-devtools/agents-md.svg)](https://agentmods.dev/instructions/yeaight7/awesome-ai-devtools/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/yeaight7/awesome-ai-devtools/agents-md"><img src="https://agentmods.dev/badge/instructions/yeaight7/awesome-ai-devtools/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 344 This file is loaded in full into every session.
When invoked 344 The same file — it is already loaded in full.
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 $0.00344 $0.00344
Opus 5 $0.00172 $0.00172
Sonnet 5 $0.00069 $0.00069
Haiku 4.5 $0.00034 $0.00034

Measured 4d ago against content hash f578477687cd, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

awesome-ai-devtools 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.

AGENTS.md · 28 lines

What it actually says

Agent Guidance

This repository is metadata-first. Do not hand-edit generated tool listings in README.md or docs/COMPARISON.md — both are generated.

Source Of Truth

  • Edit data/tools.yml, data/categories.yml, and data/tags.yml.
  • Run npm run sort after changing tool metadata.
  • Run npm run generate after changing data or README generation.
  • Run npm test before claiming completion.
  • Network-dependent maintenance (npm run check:links, npm run check:stale) runs in the scheduled workflow, never in PR validation. See docs/maintenance-policy.md.

Data Rules

  • Use official sources wherever possible.
  • Do not invent metadata. Use not specified for uncertain license, deployment, or source-model facts.
  • Keep descriptions factual, neutral, and 40-180 characters.
  • Do not add subjective rankings, scores, hype language, or launch strategy. Validation rejects promotional description language and warns on soft subjective wording.
  • Do not add large batches manually. Use scripts/import-candidates.ts for candidate batches, then review entries before promotion.
  • Imported entries remain drafts until sources, categories, and uncertain fields are verified.
  • When promoting a multi-category tool to reviewed, set primary_category to the single category slug that best represents its primary workflow. Validation will block promotion without it.

Scope Boundaries

  • Do not add dependencies, CI changes, scraping, auth, deployment, or website work unless explicitly requested.
  • Keep diffs small and reversible.
  • Public contribution policy belongs in CONTRIBUTING.md and docs/, not only here.
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 · 28 lines · 344 tokens per session scan A f578477687cd

Subscribe to this mod's changes

awesome-ai-devtools AGENTS.md is an instructions file published in the GitHub repository yeaight7/awesome-ai-devtools (10 stars, last pushed 6d ago), licensed MIT. It adds 344 tokens to every session, about $0.0017 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.