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/husniadil/ekstend/agents-mdgit clone --depth 1 https://github.com/husniadil/ekstendWrote 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/husniadil/ekstend/agents-md)<a href="https://agentmods.dev/instructions/husniadil/ekstend/agents-md"><img src="https://agentmods.dev/badge/instructions/husniadil/ekstend/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 | $0.01572 | $0.01572 |
| Opus 5 | $0.00786 | $0.00786 |
| Sonnet 5 | $0.00314 | $0.00314 |
| Haiku 4.5 | $0.00157 | $0.00157 |
Grade A, and why
ekstend 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 — 175 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Instructions for AI coding agents working on this project.
Project Overview
This is a Claude Code plugins repository containing reusable plugins that extend Claude Code's capabilities. Plugins are installed via the Claude Code plugin marketplace system.
Repository structure:
.claude-plugin/marketplace.json # Marketplace metadata (lists all plugins)
plugins/
<plugin-name>/
.claude-plugin/plugin.json # Plugin metadata
CLAUDE.md # Redirects to AGENTS.md
AGENTS.md # Plugin-specific instructions for AI agents
README.md # Plugin documentation
skills/ # Skill definitions
<skill-name>/
SKILL.md # Skill instructions (frontmatter + markdown)
references/ # Detailed reference docs
scripts/ # Python scripts
tests/ # Unit tests (optional)
Current Plugins
- ultrathink: Sequential thinking CLI for multi-step problem solving with confidence tracking and assumption management. Python-based, runs via
uv run. - skill-creator: Guide for creating effective skills that extend Claude's capabilities with specialized knowledge, workflows, or tool integrations. Includes utility scripts for initializing, validating, and packaging skills. Licensed under Apache 2.0.
- database: Unified access to MySQL, PostgreSQL, SQLite databases, and Redis key-value stores via CLI for querying, schema/key exploration, and data management. Auto-detects database type from context. Pure instruction-based skill (no scripts).
- ideate: Facilitation-first brainstorming skill that helps users unlock their own ideas through structured questioning (EECCA workflow) and expansion techniques. Pure instruction-based skill (no scripts).
- code-review: Iterative code-review toolkit bundling two skills.
code-reviewitself finds gaps proactively (PR diff or holistic codebase), with business-logic awareness, end-to-end integration tracing (frontend → backend → database → external APIs), dependency grounding against pinned versions, and a tracked fix loop (TaskCreate/TaskUpdate).address-pr-reviewreacts to existing GitHub PR comments — validate (Valid / Partial / Invalid / Defer / Repeat), fix, reply, and resolve threads viaghGraphQL/REST. 10 gap categories. Pure instruction-based skills (no scripts). - interview: Deep requirements gathering skill that interviews users through thoughtful, in-depth questions before implementation. Uses CDEEPER workflow (Contextualize, Discover, Explore, Edge, Prioritize, Experience, Ready) to uncover hidden requirements, edge cases, and trade-offs. Pure instruction-based skill (no scripts).
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 · 175 lines · 1,572 tokens per session scan A 5cf0e7b63ce9
ekstend AGENTS.md is an instructions file published in the GitHub repository husniadil/ekstend (1 stars, last pushed 4mo ago), licensed MIT. It adds 1,572 tokens to every session, about $0.0079 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
gh-review-loop CLAUDE.md
Instructions for OrenAshkenazy/gh-review-loop, covering claude.md, skill.md placement rule, test runner, if installed via homebrew on apple silicon and or run pytest from a virtual environment.
backchain-plugins CLAUDE.md
Instructions for backchainai/backchain-plugins, covering claude.md, repository overview, plugins, architecture and key patterns.
gfl-marketplace CLAUDE.md
Claude Code instructions for gf-labs/gfl-marketplace, covering claude.md, what this is, how local development works, settings.json registration and adding a plugin.
river-review GEMINI.md
Gemini CLI instructions for s977043/river-review, covering gemini instructions (river-review), 必須チェック, gemini-specific tips, prompt assembly and development tips.
ship-it open-pr.instructions.md
Instructions for khrichtchatyi/ship-it: When the user asks to open, create, or submit a pull request, follow the skill in skills/open-pr/SKILL.md in full: verify gh is authenticated, resolve the target repository and default branch, push the current branch, open one pull request with a title and body derived from the…
agent-skills CLAUDE.md
Instructions for mindbox-cloud/agent-skills, covering agent-skills — developer guide for claude code, repository purpose, repository structure, how to add a new plugin and step 1 — create the directory structure.