agentmods.dev

tank AGENTS.md

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

38 27d ago A scan 8,834 tokens original MIT
View the source file tankpkg/tank
Install

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.

agentmods
npx agentmods add instructions/tankpkg/tank/agents-md
Clone the repo
git clone --depth 1 https://github.com/tankpkg/tank

Made for: Codex, OpenCode.

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. Scan, not verified.
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 $0.08834 $0.08834
Opus 5 $0.04417 $0.04417
Sonnet 5 $0.01767 $0.01767
Haiku 4.5 $0.00883 $0.00883

Measured 2d ago against content hash be4463428853, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, 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 2d 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. 2d 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 27d ago), licensed MIT. It adds 8,834 tokens to every session, about $0.0442 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 2026-08-30.

Securityai-agentsclipackage-managerregistryskills
Related

Other instructions, from other repositories

agentregistry AGENTS.md

Instructions for agentregistry-dev/agentregistry, covering agents.md - development guidelines, project overview, architecture, directory structure and layer responsibilities.

agentregistry-dev/agentregistry · 3,622 tokens

agentregistry copilot-instructions.md

Instructions for agentregistry-dev/agentregistry, covering github copilot instructions and keeping the pr description up-to-date.

agentregistry-dev/agentregistry · 290 tokens

lola AGENTS.md

Instructions for LobsterTrap/lola, covering lola — agent instructions, working in this repo, development commands, python and go.

LobsterTrap/lola · 1,209 tokens

lola CLAUDE.md

Instructions for LobsterTrap/lola, covering active technologies and recent changes.

LobsterTrap/lola · 412 tokens

agentregistry CLAUDE.md

Instructions for agentregistry-dev/agentregistry, a project described as: Fast-track AI innovation with a centralized, trusted, curated registry.

agentregistry-dev/agentregistry · 3 tokens

skillshub CLAUDE.md

Claude Code instructions for EYH0602/skillshub, covering agents.md - project context for coding agents, project purpose, development, building and testing locally.

EYH0602/skillshub · 586 tokens