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.
npx agentmods add instructions/mytech-today-now/augment-extensions/agents-mdgit clone --depth 1 https://github.com/mytech-today-now/augment-extensionsWrote 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/mytech-today-now/augment-extensions/agents-md)<a href="https://agentmods.dev/instructions/mytech-today-now/augment-extensions/agents-md"><img src="https://agentmods.dev/badge/instructions/mytech-today-now/augment-extensions/agents-md.svg" alt="Measured on agentmods" 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 | $0.04117 | $0.04117 |
| Opus 5 | $0.02058 | $0.02058 |
| Sonnet 5 | $0.00823 | $0.00823 |
| Haiku 4.5 | $0.00412 | $0.00412 |
Grade A, and why
augment-extensions 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.
How it starts
The opening of the file, as written. The whole thing — 473 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Augment Extensions - AI Agent Integration
This repository provides extension modules for Augment Code AI that exceed the standard .augment/ character limit.
For AI Agents
Discovery
You can discover and use extension modules through the augx CLI:
# List all available modules
augx list
# Show module details
augx show <module-name>
# Search for modules
augx search <keyword>
Usage in Projects
When working on a project that has Augment Extensions linked:
- Check linked modules:
augx list --linked - View module content:
augx show <module-name> - Apply module rules: Follow the guidelines in the module's rules/ directory
Module Structure
Each module contains:
module.json- Metadata and configurationrules/- Markdown files with detailed guidelinesexamples/- Code examples demonstrating best practicesREADME.md- Module overview
Integration Workflow
- Human initializes:
augx init - Human links modules:
augx link coding-standards/typescript - AI agent queries:
augx show typescript-standards - AI agent applies rules from module content
CLI Commands Reference
augx list- List all available modulesaugx list --linked- List modules linked to current projectaugx show <module>- Display module contentaugx show linked- Show all linked modulesaugx show all- Show all available modulesaugx search <term>- Search for modulesaugx update- Update all linked modulesaugx version- Show CLI version
Command Help Reference
When augx init is run, the CLI automatically generates .augment/COMMAND_HELP.md containing comprehensive help documentation for all detected workflow tools (Beads, OpenSpec, Augx).
For AI Agents:
- Check for help reference: Look for
.augment/COMMAND_HELP.mdin the project - Use for command discovery: Reference the file to learn available commands and their syntax
- Generate accurate commands: Use the help text to construct correct command invocations
- Understand tool capabilities: Learn what each tool can do without executing commands
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.
- 4d ago First seen · 473 lines · 4,117 tokens per session scan A 6c8afdecfbcc
augment-extensions AGENTS.md is an instructions file published in the GitHub repository mytech-today-now/augment-extensions (4 stars, last pushed 3mo ago), licensed MIT. It adds 4,117 tokens to every session, about $0.0206 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.
Other instructions, from other repositories
figma-console-mcp CLAUDE.md
Claude Code instructions for southleft/figma-console-mcp, covering figma console mcp, build & test, release process, known issues and architecture.
AllBeads CLAUDE.md
Instructions for thrashr888/AllBeads, covering claude.md, project overview, what allbeads does, current state (v0.2.0) and rust development commands.
flow AGENTS.md
Instructions for cofin/flow: Flow is a toolkit for context-driven development. It has no flow executable; invoke the Flow skill or a /flow: command.
get-shit-pretty CLAUDE.md
Claude Code instructions for jubscodes/get-shit-pretty, covering gsp — get shit pretty, must-always / must-never, git workflow, this repository and architecture.
super-ux CLAUDE.md
Claude Code instructions for ssheleg/super-ux, covering claude.md — super-ux, where the artifacts are, gates, adding a skill and adding a hard rule.
phonebook CLAUDE.md
Claude Code instructions for stag-build/phonebook, covering @stag-build/phonebook and model/agent delegation (token budget).