Borrowing it
Nothing to install: this file belongs to kreek/consult. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/kreek/consult/main/AGENTS.mdgit clone --depth 1 https://github.com/kreek/consultWrote 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.
[](https://agentmods.dev/instructions/kreek/consult/agents-md)<a href="https://agentmods.dev/instructions/kreek/consult/agents-md"><img src="https://agentmods.dev/badge/instructions/kreek/consult/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/instructions/kreek/consult/agents-md"><img src="https://agentmods.dev/badge/instructions/kreek/consult/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.04250 | $0.04250 |
| Opus 5.5 | $0.01700 | $0.01700 |
| Sonnet 5.5 | $0.00850 | $0.00850 |
| Haiku 4.5 | $0.00425 | $0.00425 |
Grade B, and why
consult AGENTS.md scanned grade B with 1 finding 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 27d 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.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
`plugin/skills/` mirror under `~/.gemini/config/plugins/consult`. How it starts
The opening of the file, as written. The whole thing — 344 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
This file provides guidance to coding agents (Claude Code, Codex, Cursor, and
others that read AGENTS.md) when working with code in this repository.
What this repo is
Consult is a portable skill pack for coding agents (Claude Code,
Codex, Cursor, Copilot, Gemini CLI, Google Antigravity, OpenCode, Pi,
Windsurf). It ships
prose (SKILL.md files plus a few maintenance helpers), not application code.
Most edits are to skill bodies, the top-level AGENTS.md, or the
README.md. There is no application build or service to run; tests cover
repo maintenance helpers, plugin packaging, and extension packages.
Source of truth and mirrors
- Canonical skills:
agents/.agents/skills/<name>/SKILL.md. Every skill lives here; siblings may addagents/,references/, andscripts/. - Repo instructions:
AGENTS.mdis the main portable instruction file in the repo.CLAUDE.mdmirrors the same maintainer guidance for hosts that read Claude-specific files. Normal Consult use relies on skill frontmatter, plugin metadata, theworkflowskill, and the plugin SessionStart hook that tells the agent to loadworkflowbefore non-trivial code work; users do not need to install or merge system instruction files. - Claude Code plugin mirror:
plugin/skills/<name>contains generated copies of canonical skills fromagents/.agents/skills/<name>..claude-plugin/marketplace.jsonpoints Claude Code at theplugin/root, whereplugin/.claude-plugin/plugin.jsonexposes namespaced/consult:<skill>slash commands. - Codex plugin package:
.agents/plugins/marketplace.jsonpoints Codex at theplugin/root, andplugin/.codex-plugin/plugin.jsonexposes the same generated skill mirror to Codex as a plugin. Keep the Codex marketplace and manifest in sync with Claude plugin packaging. - Plugin SessionStart hook:
plugin/hooks/hooks.jsonis hand-written, not generated. Claude Code and Codex discover it by convention, so no manifest declareshooks. It holds exactly one SessionStart command that prints the routing line, and the validator rejects anything more. Codex runs it only after the user trusts it. Cursor and Antigravity also find the file: Antigravity cannot parse the Claude Code format and still loads the skills, and whether Cursor uses the plain-text output is unverified. - Cursor plugin package:
.cursor-plugin/marketplace.jsonpoints Cursor at theplugin/root, andplugin/.cursor-plugin/plugin.jsonexposes the same generated skill mirror as a Cursor plugin whose manifest declares no hooks or MCP. Keep the Cursor marketplace and manifest in sync with Claude plugin packaging. - Google Antigravity plugin package:
plugin/plugin.jsonis the Antigravity marker for Consult. Local installs create an Antigravity plugin directory that links onlyplugin/plugin.jsonand the generatedplugin/skills/mirror under~/.gemini/config/plugins/consult. - Install layout:
agents/is a GNU Stow package../setup.shis the one-click local installer: it explains the actions, asks for approval, runs Stow to link the shared skills under~/.agents/, fans those out to per-tool locations, prunes manual Codex links when the Consult Codex plugin is installed, and re-runs the plugin-sync. SystemAGENTS.md/CLAUDE.mdfiles are not part of Consult installation.
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.
- 27d ago Changed · +3 lines · +63 tokens per session 6aa9bfc22e50
- 1mo ago Changed · +13 lines · +201 tokens per session 0ef53673dc8c
- 1mo ago Changed · +17 lines · +223 tokens per session f8008d0d94d6
- 2mo ago First seen · 311 lines · 3,763 tokens per session scan B cd0918e55e7e
consult AGENTS.md is an instructions file published in the GitHub repository kreek/consult (1 stars, last pushed 27d ago), licensed MIT. It adds 4,250 tokens to every session, about $0.0170 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other instructions, from other repositories
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, cache eligibility and rollout and applying the notice (cutover).
langchain AGENTS.md
AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.
vscode copilot-instructions.md
Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).
deno copilot-instructions.md
Copilot instructions for denoland/deno, covering deno development guide for github copilot, network access, high level overview, key directories and key files to understand first.