agentdeck CLAUDE.md

A set of project instructions for AgentDeck, a runtime for building and running workflows that use multiple AI agents. It covers the project's design, code, architecture, testing, and verification rules.

In plain words
What is it for?
Use it when changing AgentDeck code or reviewing its structure. It helps agents follow the required coding standards, runtime contracts, tests, dependencies, and repository conventions.
Why use it?
It gives coding agents one shared set of rules to follow, reducing inconsistent changes and missed checks. It also explains where different project decisions are recorded.

Instructions file

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/agentdecksdk/agentdeck/claude-md
Clone the repo
git clone --depth 1 https://github.com/agentdecksdk/agentdeck
Per session 1,435 This file is loaded in full into every session.
When invoked 1,435 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 $0.01435 $0.01435
Opus 5 $0.00718 $0.00718
Sonnet 5 $0.00287 $0.00287
Haiku 4.5 $0.00144 $0.00144

Measured 2d ago against content hash 480e061430f4, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

agentdeck CLAUDE.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.

CLAUDE.md · 70 lines

How it starts

The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AgentDeck

AgentDeck is a declarative runtime harness for multi-agent systems and workflows (OpenAI Agents SDK, plus AgentDeck-native @tool/@workflow).

Core standards: docs/engineering/: the linked suite of binding engineering law:

  1. docs/engineering/principles.md: Product philosophy & North Star.
  2. docs/engineering/coding-standards.md: Binding front door for every code change.
  3. docs/engineering/coding-agents.md: Mandatory rules for coding agents.
  4. Specialized standards: architecture.md, runtime-contracts.md, testing.md, dependencies.md, repository-policy.md, import-boundaries.md.
  5. docs/patterns/: the project's taste as real good/bad pairs. Read the file for your concern before writing; match the good side.

1. Product Philosophy & North Star

Make powerful agentic systems feel obvious to build, compose, run, and operate. Great software does the hard work so its users do not have to. Simple on the outside, elegant on the inside.

  • User owns intent, AgentDeck owns machinery: Users define agents, tools, workflows, skills, and context. AgentDeck manages run identity, execution lifecycle, persistence, event streams, cancellation, and concurrency.
  • Abstractions must delete complexity: An abstraction is successful only when the caller needs to know less. Never leak internal plumbing (stores, resolvers, internal contexts, log keys) into public user APIs.
  • One obvious path first: One clean, standard path for common tasks (await deck.run(...)). Advanced knobs remain escape hatches, never obstacles.
  • Conciseness is mandatory: No fluff, no sprawling prose. If one sentence suffices, write one sentence. Code, comments, docs, PR descriptions, and issue specs must be terse, precise, and dense with signal.
  • No em dashes: Never use the - character in any documentation, code, comments, or agent output. Use a regular hyphen -, colon :, or separate into distinct sentences.

Read the full file on GitHub · 70 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 · 70 lines · 1,435 tokens per session scan A 480e061430f4

Subscribe to this mod's changes

agentdeck CLAUDE.md is an instructions file published in the GitHub repository agentdecksdk/agentdeck (2 stars, last pushed 3d ago), licensed MIT. It adds 1,435 tokens to every session, about $0.0072 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.