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 agents/ulises-jeremias/agent-toolkit/installgit clone --depth 1 https://github.com/ulises-jeremias/agent-toolkitWrote 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/agents/ulises-jeremias/agent-toolkit/install)<a href="https://agentmods.dev/agents/ulises-jeremias/agent-toolkit/install"><img src="https://agentmods.dev/badge/agents/ulises-jeremias/agent-toolkit/install.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 | $0.00000 | $0.00450 |
| Opus 5 | $0.00000 | $0.00225 |
| Sonnet 5 | $0.00000 | $0.00090 |
| Haiku 4.5 | $0.00000 | $0.00045 |
Grade A, and why
INSTALL 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.
What it actually says
Installing the MegaLinter sub-agents on your platform
The three definitions in this folder use the Claude Code agent format (YAML frontmatter: name, description, tools, optional model; markdown body with the instructions). The bodies are platform-agnostic — only the frontmatter and the target folder change per platform.
Load only the section matching the platform you are running on. In every case: create the target folder if missing, and ask the user before overwriting an existing file.
Claude Code
Copy the files as-is:
mkdir -p .claude/agents && cp <skill_dir>/agents/megalinter-*.md .claude/agents/
OpenCode
Target folder: .opencode/agent/. Adapt the frontmatter: set mode: subagent, translate tools to OpenCode's tools: map (e.g. bash: true, edit: false for the read-only watcher/runner), and replace model: haiku with a cheap model available in your configuration (e.g. anthropic/claude-haiku-4-5). Keep description and the body unchanged.
GitHub Copilot (custom agents)
Target folder: .github/agents/. Keep name and description in the frontmatter; drop tools/model if your Copilot version doesn't accept them; keep the body unchanged.
Codex and other platforms
If your platform documents custom agent/subagent definition files, mirror the pattern above: keep the body, translate the frontmatter to the platform's schema, place the files in the platform's agents location. If the platform only supports a single instructions file (e.g. AGENTS.md), do NOT install these files — the MegaLinter skills already degrade to inline execution.
Model guidance
megalinter-watcher and megalinter-runner do mechanical work (poll, download, digest): map them to the cheapest/fastest model tier your platform offers. megalinter-fixer edits code: leave it on the session's default model (no model override).
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.
- today First seen · 30 lines · 0 tokens per session scan A 2160d4438c93
INSTALL is an agent published in the GitHub repository ulises-jeremias/agent-toolkit (16 stars, last pushed today), licensed MIT. It costs nothing until one of its globs matches a file; then it loads 450 tokens. 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 2026-09-04.
Other agents, from other repositories
helius-integration-specialist
Specialist agent for Helius + Solana integrations — queries live blockchain data, sends transactions via Sender, sets up webhooks, streams real-time data, and routes to domain-specific skills for trading, frontend development, and protocol research.
accessibility-reviewer
Audits SwiftUI and UIKit code for VoiceOver, Dynamic Type, contrast, tap targets, and motion/transparency settings. Read-only — reports findings with file:line and the specific fix. Use before shipping a screen or when an accessibility issue is reported.
security-auditor
Security specialist for CrawlForge MCP Server. Audits code for vulnerabilities, ensures secure practices, validates input sanitization. Use PROACTIVELY before deployments and after major changes.
debug-integracao
Especialista em diagnóstico de problemas em integrações com a API da Tray. Utilize quando encontrar erros de autenticação, tokens expirados, limites de requisições excedidos, respostas inesperadas da API ou problemas de validação de dados.
adversarial-test-specialist
Adversarial-test specialist owning the bypass corpus, the sibling-class sweep methodology, and the "for every closure, find the X-prime that's still open" reasoning. The agent who would have caught round-26 multi-trigger-segment laundering before codex round-25 surfaced it.
typescript-specialist
TypeScript specialist enforcing strict mode, type system design, declaration files, and type safety across the codebase.