agentmods.dev

tank: Instructions file for Codex

AGENTS.md

tank AGENTS.md is an instructions file for Codex, OpenCode from tankpkg/tank. It costs 8,834 tokens per session, scanned A, original, MIT.

Repository instructions for Tank, a security-focused package manager for coding-agent skills. They describe its monorepo structure—a single repository containing several related projects—and explain how agents should recover context and work safely.

In plain words
What is it for?
Use them when working on Tank's command-line tool, server, registry applications, shared schemas, or scanner, especially before making repository changes.
Why use it?
They provide the background needed to navigate Tank without treating its many applications and shared packages as unrelated projects. They also define where project knowledge and active work are documented.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions CLAUDE.md; mentions AGENTS.md.

This is tankpkg/tank's own configuration. It tells Codex and OpenCode how to work on tank itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tank configures →

not rated 38repo 2mo ago A scan 8,834 tokens original MIT
View source ↗ tankpkg/tank tankpkg.dev
Reuse

Borrowing it

Nothing to install: this file belongs to tankpkg/tank. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/tankpkg/tank/main/AGENTS.md
Clone the repo
git clone --depth 1 https://github.com/tankpkg/tank

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 tank AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/tankpkg/tank/agents-md/github.svg)](https://agentmods.dev/instructions/tankpkg/tank/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/tankpkg/tank/agents-md"><img src="https://agentmods.dev/badge/instructions/tankpkg/tank/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.

agentmods 80×15 button for tank AGENTS.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/tankpkg/tank/agents-md"><img src="https://agentmods.dev/badge/instructions/tankpkg/tank/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 8,834 This file is loaded in full into every session.
When invoked 8,834 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.08834 $0.08834
Opus 5.5 $0.03534 $0.03534
Sonnet 5.5 $0.01767 $0.01767
Haiku 4.5 $0.00883 $0.00883

Measured 1mo ago against content hash be4463428853, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

tank 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 1mo 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 · 794 lines

How it starts

The opening of the file, as written. The whole thing — 794 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Tank

Security-first package manager for AI agent skills. Monorepo: CLI + MCP server + web registries + shared schemas + Python scanner. Bun workspaces. Born from ClawHavoc — 341 malicious skills, 12% of a major marketplace.

AGENTS.md and CLAUDE.md are symlinked. This file is your system prompt. Loads every context window. Every token has a cost. Keep it holy — concise, tight, agents-only.

Philosophy

  • This file + docs/ + idd/ = memory. Fresh context = amnesia. Recover here first, then open only what you need.
  • docs/ holds reference/process truth. idd/ holds intent and active initiatives.
  • Tooling-enforced rules (Biome, tsconfig, EditorConfig) do not belong here.
  • Capabilities > file paths. git log, just --list, and source code are living docs.
  • Be extremely concise — sacrifice grammar, not information. Every interaction, plan, commit, doc.

Current State

  • apps/registry = TanStack Start registry app (UI + API). Full-featured: home, skills browse/detail/search, docs (pre-rendered), login (email + GitHub + OIDC), CLI auth, publish API, admin panel (users/packages/audit CRUD), tokens, orgs.
  • On-prem: TANK_MODE=selfhosted enables setup wizard, filesystem storage, CLI binary serving. Cloud mode (TANK_MODE=cloud, default) disables all on-prem features.
  • Two deploy channels: stable (www.tankpkg.dev) and nightly (nightly.tankpkg.dev).

Context Recovery

  1. Read this file.
  2. Quick start: just install && just docker up && just db push && just dev registry
  3. find docs -name "*.md" | sort and open only the docs needed for the task.
  4. find idd -name "*.md" | sort if intent or active initiatives matter.
  5. just --list for commands.
  6. Read first:
    • docs/core/where-to-look.md
    • docs/core/deps.md
    • docs/process/methodology.md
  7. Read when relevant:
    • docs/core/architecture.md
    • docs/core/anti-patterns.md
    • docs/core/security.md
    • docs/process/testing-reference.md
    • docs/reference/packages/*
  8. git log --oneline -20 for recent decisions.
  9. Scan relevant source dirs. If docs and code conflict, code wins.

Read the full file on GitHub · 794 lines

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. 1mo ago First seen · 794 lines · 8,834 tokens per session scan A be4463428853

Subscribe to this mod's changes

tank AGENTS.md is an instructions file published in the GitHub repository tankpkg/tank (38 stars, last pushed 2mo ago), licensed MIT. It adds 8,834 tokens to every session, about $0.0353 per session on Opus 5.5. 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 2026-08-30.

ai-agentsclipackage-managerregistryskills
Related

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).

microsoft/vscode · 9,715 tokens

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.

vercel/next.js · 7,786 tokens

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).

microsoft/vscode · 5,262 tokens

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.

langchain-ai/langchain · 4,680 tokens

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).

microsoft/vscode · 2,731 tokens

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.

denoland/deno · 3,077 tokens